No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Movie forecast Guru: A Web-based DSS for Hollywood managers
Abstract
Herein we describe a Web-based DSS to help Hollywood managers make better decisions on important movie characteristics, such as, genre, super stars, technical effects, release time, etc. These parameters are used to build prediction models to classify a movie in one of nine success categories, from a “flop” to a “blockbuster”. The system employs a number of traditional and non-traditional prediction models as distributed independent experts, implemented as Web services. The paper describes the purpose and the architecture of the system, the development environment, the user assessment results, and the lessons learned as they relate to Web-based DSS development.
... Most of the studies have designed it as a classification problem where forecasting is done to determine whether a movie is likely to earn higher or lower than a certain revenue value instead of designing it as a regression model to predict earnings. Delen et al. [30] developed classification-based forecasting models using discriminant analysis, decision trees, and ANN. Zhang et al. [31] also developed a classification (six predefined categories) based prediction model using ANN as a base model. ...
... Artificial Neural Network (ANN) is one of the most used ML algorithms in academics [30]. Input passes through multiple layers of connected neurons. ...
... Average of ratings received by all the movies released between year t-5 and t-1 (where t is the release year of the current movie), which were also directed by the lead directors of the current movie 29 producer_MT_Ra ting Average of ratings received by all the movies released between year t-5 and t-1 (where t is the release year of the current movie), which were also produced by the lead producers of the current movie 30 writer_MT_Ratin g Average of ratings received by all the movies released between year t-5 and t-1 (where t is the release year of the current movie), which were also written by the lead writers of the current movie 31 ...
Moviegoers refer to online audience movie ratings before deciding to watch a movie. They are more inclined to watch a movie with a high average rating. We develop a system to predict average audience movie ratings based on the lead cast and crew at an early stage of movie production. After valuing multiple scenarios, investors can use our study to select the lead cast and crew objectively. Judicious selection of the key cast and crew is extremely important as investors commit to large sums of money as professional fees while signing contracts with them. Our study uses a relatively large sample of 1687 Indian movies spread across 10+ languages released in India between 2010 and 2019 to identify the important predictors influencing average audience movie rating. Identification of important predictors improves the explainability of the prediction model, which increases the investors’ trust in the predicted values. The best model, random forest, reduces the baseline prediction error of the average rating by 10.21%.
... Movies are complex products [18] and because of this complexity the movie industry involves a lot of risk. To mitigate these risks, decision makers such as producers, investors, distributors, exhibitors and marketers [20] try to predict box office revenues to optimize production and marketing [68]. Decision makers need predictive models in the pre-production phase to help them make decisions pertaining to production factors such as budget [29], and casting. ...
... Given the high financial stakes involved in marketing motion pictures [30], and hence the importance of these decisions, accurate box office predictions are desired. However, box office prediction has been shown to be a task of great difficulty [20] and understanding the predictive ability of new data sources is therefore important. ...
... To ensure that our results are reliable, we compare both platforms using several algorithms: regularized linear regression (LR), k-nearest neighbors (KN), decision trees (DT), bagged trees (BT), random forest (RF), gradient boosting (GB) and neural networks (NN). We included these algorithms since they have been shown to have superior performance in predicting box office sales and firm performance in general [72,20]. ...
This paper aims to determine the power of social media data (Facebook and Twitter) in predicting box office sales, which platforms, data types and variables are the most important and why. To do so, we compare several models based on movie data, Facebook data, and Twitter data. We benchmark these model comparisons using various prediction algorithms. Next, we apply information-fusion sensitivity analysis to evaluate which variables are driving the predictive performance. Our analysis shows that social media data significantly increases the predictive power of traditional box office prediction models. Facebook data clearly outperform Twitter data and including user-generated content next to marketer-generated always improves predictive power. Our sensitivity analysis reveals that volume and valence based combination variables pertaining to Facebook comments are the most important variables. Furthermore, we provide an in-depth analysis of the potential mechanisms driving differential predictive ability of Facebook and Twitter. Our findings suggest that Twitter has less of an impact on box office sales than Facebook because Twitter users have less source credibility than Facebook users. Our results are important for practitioners, marketers and academics who want to employ social media data for box office sales predictions.
... A number of studies related to box-office performance prediction have already been conducted (Basuroy et al., 2003;Sharda and Delen, 2006;Zhang et al., 2009;Lipizzi et al., 2016). Several factors influencing box-office performance have been identified, including the movie genre, director, actors and plot summary as well as marketing activities used to promote the movies (Chintagunta et al., 2010;Delen et al., 2007;Ding et al., 2017;Hur et al., 2016). ...
... Table I summarized previous studies on the prediction of box-office performance. Many of previous studies have developed box-office prediction models by using basic movie information such as movie genre, director and actors, as independent variables (Chintagunta et al., 2010;Delen et al., 2007;Ding et al., 2017;Oh et al., 2017;Sharda and Delen, 2006;Zhang et al., 2009). Sharda and Delen (2006) selected 834 movies released from 1998 to 2002 and used artificial neural network (ANN) to predict the box-office performance by considering factors such as movie genre, motion picture rating system, competitors (i.e. ...
... A sensitivity analysis was later performed to investigate the effects of various movie factors on box-office performance prediction results, in which the top three factors were number of theaters that showed the movies, whether the movies had superb special effects and whether the movies starred famous actors. Delen et al. (2007) collected the data of 849 movies released from 1998 to 2002 to develop a decision support system for box-office prediction. Movie genre, MPAA rating, actors, competitor, whether the movie was a sequel, special effect and the number of theaters that showed the movie were set as the independent variables and five different classification techniques (i.e. ...
Purpose
The purpose of this paper is to combine basic movie information factors, external factors and review factors, to predict box-office performance and identify the most crucial factor of influence for box-office performance.
Design/methodology/approach
Five movie genres and first-week movie reviews found on IMDb were collected. The movie reviews were quantified using sentiment analysis tools SentiStrength and Stanford CoreNLP, in which quantified data were combined with basic movie information and external environment factors to predict movie box-office performance. A movie box-office performance prediction model was then developed using data mining (DM) technologies with M5 model trees (M5P), linear regression (LR) and support vector regression (SVR), after which movie box-office performance predictions were made.
Findings
The results of this paper showed that the inclusion of movie reviews generated more accurate prediction results. Concerning movie review-related factors, the one that exhibited the greatest effect on box-office performance was the number of movie reviews made, whereas movie review content only displayed an effect on box-office performance for specific movie genres.
Research limitations/implications
Because this paper collected movie data from the IMDb, the data were limited and primarily consisted of movies released in the USA; data pertaining to less popular movies or those released outside of the USA were, thus, insufficient.
Practical implications
This paper helps to verify whether the consideration of the features extracted from movie reviews can improve the performance of movie box-office.
Originality/value
Through various DM technologies, this paper shows that movie reviews enhanced the accuracy of box-office performance predictions and the content of movie reviews has an effect on box-office performance.
... In order to resolve this issue, we propose an automated decision support tool guided by the final stage (management process) of the CAM theory. For example, Delen, Sharda, & Kumar [15] developed an automated web-based tool integrating prediction models to provide Hollywood producers with a way of classifying a movie into one of nine success categories, ranging from flops to blockbusters. ...
... Trial and error and experimentation are required in order to find the best model for each scenario [42]. Furthermore, Delen et al. recommend incorporating the knowledge of multiple experts in the development and training of a model [15]. To develop an appropriate model, companies should consult with experts in the relevant field and choose the appropriate attributes based on their experience and geographic location. ...
Productivity losses caused by absenteeism at work cost U.S. employers billions of dollars each year. In addition, employers typically spend a considerable amount of time managing employees who perform poorly. By using predictive analytics and machine learning algorithms, organizations can make better decisions, thereby increasing organizational productivity, reducing costs, and improving efficiency. Thus, in this paper we propose hybrid optimization methods in order to find the most parsimonious model for absenteeism classification. We utilized data from a Brazilian courier company. In order to categorize absenteeism classes, we preprocessed the data, selected the attributes via multiple methods, balanced the dataset using the synthetic minority over-sampling method, and then employed four methods of machine learning classification: Support Vector Machine (SVM), Multinomial Logistic Regression (MLR), Artificial Neural Network (ANN), and Random Forest (RF). We selected the best model based on several validation scores, and compared its performance against the existing model. Furthermore, project managers may lack experience in machine learning, or may not have the time to spend developing machine learning algorithms. Thus, we propose a web-based interactive tool supported by cognitive analytics management (CAM) theory. The web-based decision tool enables managers to make more informed decisions, and can be used without any prior knowledge of machine learning. Understanding absenteeism patterns can assist managers in revising policies or creating new arrangements to reduce absences in the workplace, financial losses, and the probability of economic insolvency.
... (3) From each K optimal neural network, K importance values [44] of each product attribute are calculated based on SHAP method. (4) Based on the information fusion algorithm, the K importance values are combined [45]. ...
... The information fusion algorithm is used to combine the K importance values of each product attribute [45]. Numerous studies have employed this algorithm for combining the effect of input variables in machine learning models. ...
The importance-performance analysis (IPA) is a widely used technique to guide strategic planning for the improvement of customer satisfaction. Compared to surveys, numerous online reviews can be easily collected at a lower cost, therefore online reviews provide a promising source for the IPA. This paper proposes an approach for conducting the IPA from online reviews for product design. Product attributes from online reviews are first identified by latent Dirichlet allocation. The performance of the identified attributes is subsequently estimated by the aspect-based sentiment analysis of IBM Watson. Finally, the importance of the identified attributes is estimated by evaluating the effect of sentiments of each product attribute on the overall rating using an explainable deep neural network. A Shapley additive explanation-based method is proposed to estimate the importance values of product attributes with a low variance by combining the effect of the input features from multiple optimal neural networks with a high performance. A case study of smartphones is presented to demonstrate the proposed approach. The performance and importance estimates of the proposed approach are compared to those of previous sentiment analysis and neural network-based method, and the results exhibit that the former can perform IPA more reliably. The proposed approach uses minimal manual operation and can support companies to take decisions rapidly and effectively, compared to survey-based methods.
... Previous studies have suggested statistical methods or methods based on machine learning for box office predictions. Examples include regression models (Elliott and Simmons, 2008) or support vector regressions (Kim et al., 2015;Liu et al., 2016), neural networks (Delen et al., 2007), and Bayesian networks (Lee and Chang, 2009). ...
... This study converts each box office revenue level for 3 weeks into a categorical variable according to whether the revenue is in the top 20% of the revenue distribution (1 or 0); this discretization approach for a dependent variable has been applied in conjunction with machine learning methods for the classification of box office revenue or other types to make many learning algorithms faster and more accurate for both users and experts, and discretization approaches are easier to explain, understand, and use (Delen et al., 2007;Liu et al., 2002), as this study assumes that finding movies with results in the top 20% of box office revenue is of great concern to movie producers and distributors as opposed to predicting revenue accurately. Further, as the purpose of this study is to compare the prediction performance outcomes between high and low review or reviewer subsamples and not to forecast revenue levels accurately, the study intends to use the categorical variable of box office revenue in relation to machine learning methods. ...
While electronic word-of-mouth (eWOM) variables, such as volume and valence have been posited in previous studies to consistently affect product sales, there is a lack of studies on the different contexts and outcomes that affect the importance of eWOM variables. In order to fill this gap, this study attempts to use the helpfulness of reviews and reviewers as moderators to predict box office revenue, comparing the prediction performances of business intelligence (BI) methods (random forest, decision trees using boosting, the k-nearest neighbor method, discriminant analysis) using eWOM between high and low review or reviewer helpfulness subsample in the Korean movie market scrawled from the Naver Movies website. The results of applying machine learning methods show that movies with more helpful reviews or those that are reviewed by more helpful reviewers show greater prediction performance, and review and reviewer helpfulness improve the prediction power of eWOM for box office revenue. The prediction performance will improve if the characteristics of eWOM are likely to be combined to contribute to box office revenue to a greater extent.
... However, such (information-extraction) processes not only necessitate the domain-expertise but also expertise in machine learning, in addition to the software/coding skills. As a result of this requirement, automated machine learning-based prediction tools were developed in a variety of fields (Dag et al., 2016;Delen et al., 2007;Hsieh et al., 2012) for practitioners' use as a decision support mechanism. Such tools have brought invaluable advantages to field practitioners (managers, doctors, engineers, etc.) since they serve as a complementary tool in the events that these field experts do not have sufficient knowledge about the data extraction/prediction process. ...
... For example, Delen et al. (2007) developed a webbased automated tool (Movie Forecast Guru -MFG) to facilitate Hollywood managers' decision-making processes with important movie characteristics. The automated tool was built upon four different types of models: artificial neural network, decision trees, ordinal logistics regression, and discriminant analysis. ...
This study aims to develop a decision support tool for identifying the point velocity profiles in rivers. The tool enables managers to make timely and accurate decisions, thereby eliminating a substantial amount of time, cost, and effort spent on measurement procedures. In the proposed study, three machine learning classification algorithms, Artificial Neural Networks (ANN), Classification & Regression Trees (C&RT) and Tree Augmented Naïve Bayes (TAN) along with Multinomial Logistic Regression (MLR), are employed to classify the point velocities in rivers. The results showed that ANN has outperformed the other classification algorithms in predicting the outcome that was converted into 10 ordinal classes, by achieving the accuracy level of 0.46. Accordingly, a decision support tool incorporating ANN has been developed. Such a tool can be utilized by end-users (managers/practitioners) without any expertise in the machine learning field. This tool also helps in achieving success for financial investors and other relevant stakeholders.
... In the film industry, the investors are expected to make the best decisions involved in lots of funds in the shortest possible time [1]. According to Schwartz [2], "Industry estimates reveal that 60 percent or more of movies produced each year are box-office flops, those that do resonate with viewers can generate a pretty penny for investors". ...
... If investment decisions fail, the costs of these mistakes for consumers are only the ticket price and an opportunity cost, but the costs for investors or producers are highly expensive [9]. Success (or mere survivability) largely depends on quickly aligning the organizational resources, like genre, director, super stars, advertising, technical effects, release time, etc. [1,10]. The main factors affecting the financial success of a movie are of great use in making investment decisions. ...
Academic research pertaining to the marketing of film industry has identified advertising, film-making, and star power as the important factors influencing a movie’s market performance. Prior research, however, has not investigated the joint influences of these factors. The current study has extended previous research by analyzing the investment decision of studios or investors. In order to analyze the optimal film investment decision in advertising, film-making, and stars power, this paper develops a goodwill model and system dynamic (SD) model, which allow us to disentangle the effects of advertising, film-making, and star power on film market performance. The results show that the film producer should increasingly lay emphasis on investing in advertising to absorb moviegoers’ attention. Then the film producer should focus on investing in film-making when film quality has a great impact on the movie's reputation and audience's viewing decision. Furthermore, the film producer should pay more attention to the higher cost-performance stars who have more reasonable remuneration, better acting skills, and bigger box-office guarantee. Moreover, the numerical analysis reveals that rational audience contribute more than fans to a movie's box-office and bankable stars contribute more than high-profile stars to a movie's returns. Through SD simulation analysis, the film series yields higher profits than new theme movies although the cost of investment is the same.
... Regarding the first subject category, a number of studies have attempted to 2 Computational Intelligence and Neuroscience Two scenarios under three forecasting horizons Scenario 1: competition, WOM, machine learning, and forecasting combination Scenario 2: WOM, competition, machine learning, and forecasting combination determine significant factors and assess their impacts on or their relative importance in box office forecasting. Among the numerous explanatory variables tested, the following three types of factors have been found to be significant: (i) factors concerning movie characteristics, that is, screening statistics data, such as the star, director, genre, sequels, ratings, distributors, production, and marketing budgets, and the number of screens (or screening schedules) [10][11][12][13][14][15][16], (ii) competition factors reflecting market conditions, such as the number of existing and newly introduced movies [11,17,18], and (iii) word-of-mouth (WOM) effects, such as the intensity of interest and the level of preference derived from user ratings and social network services (SNS) [18][19][20][21][22]. ...
... Regarding the second subject category, most proposed forecasting algorithms fall into one of the following three subgroups: (a) a statistical learning model, such as linear regression and probabilistic models [1,10,13,[23][24][25][26], (b) time-series forecasting models, such as diffusion models and the vector autoregression method [27][28][29][30], and (c) sophisticated machine learning-based models, such as artificial neural networks (ANN) [12,31]. ...
Accurate box office forecasting models are developed by considering competition and word-of-mouth (WOM) effects in addition to screening-related information. Nationality, genre, ratings, and distributors of motion pictures running concurrently with the target motion picture are used to describe the competition, whereas the numbers of informative, positive, and negative mentions posted on social network services (SNS) are used to gauge the atmosphere spread by WOM. Among these candidate variables, only significant variables are selected by genetic algorithm (GA), based on which machine learning algorithms are trained to build forecasting models. The forecasts are combined to improve forecasting performance. Experimental results on the Korean film market show that the forecasting accuracy in early screening periods can be significantly improved by considering competition. In addition, WOM has a stronger influence on total box office forecasting. Considering both competition and WOM improves forecasting performance to a larger extent than when only one of them is considered.
... Data collection is done for big enough intervals to include the financial crisis effect and four DM models are implemented and compared with each other [26,32,50,31], logistic regression, decision trees (DT), neural network (NN) and support vector machine. LR and DT have the advantage of fitting models that tend to be easily understood by humans, while also providing good predictions in classification tasks. ...
... For instance, SVM provided better results in [32,31], comparable NN and SVM performances were obtained in [28], while DT outperformed NN and SVM in [93]. These differences in performance emphasize the impact of the problem context and provide a strong reason to test several techniques when addressing a problem before choosing one of them [46]. ...
Nowadays, the economic and social nature of contemporary business organizations chiefly banks binds them to face with the sheer volume of data and information and the key to commercial success in this area is the proper use of data for making better, faster and flawless decisions. To achieve this goal organizations requires strong and effective tools to enable them in automating task analysis, decision-making, strategy formulation and risk prediction to prevent bankruptcy and fraud .Business Intelligence is a set of skills, technologies and application systems used to collect, store, analyze and create effective access to the task to help organizations better understand the business context and make accurate decision timely and respond quickly toward inflation, rate fluctuations and the market price. In this paper we review recent literature in the search for trends in business intelligence applications for the banking industry and its challenges and finally some articles that comprise this special issue are introduced and characterized in terms of business intelligence research framework.
... The movie industry is constantly changing to meet the ever-evolving needs of audiences. As such, understanding the components that contribute to the success of a movie is essential for producers, investors, and distributors to make informed decisions [10,24]. Factors such as marketing strategies, budget, genre, cast, and audience reception all have an impact on a movie's revenue [19]. ...
In the era of invasive social media and advanced artificial intelligence, sentiment analysis has become a vital tool for e-commerce and businesses to grasp user needs and monitor brand perception. This is particularly relevant in the film industry, where understanding the determinants of a movie’s pre-release performance is crucial for producers and investors. Traditional methods often rely on complex algorithms that lack transparency in elucidating the relationship between key risk factors and movie outcomes. This study addresses this gap by employing an explainable analytics framework to investigate the impact of various social media post characteristics on movie performance before its release. Initially, an exploratory data analysis was undertaken to identify significant risk factors associated with movie failures. Subsequently, the study segmented the analysis into three risk categories—low, moderate, and high risk—and applied conventional machine learning models to forecast the likelihood of failure within each category. The culmination of this research involved the application of a SHapley Additive exPlanation (SHAP) model, which provided insightful interpretations of how different risk factors contribute to the potential success or failure of movies. By integrating SHAP for interpretability, this research offers novel insights into the predictive dynamics of movie performance, paving the way for informed decision-making in the film industry.
... Model fusion is a well-established strategy that combines information from multiple PU models (on PUtree) to make the prediction [21]. This approach has found widespread applications in various domains, including electronic health record analysis [21], temperature forecasting [26], and movie recommendation [11]. While fusion methods have been extensively studied in supervised learning scenarios, their application in the PU learning setting remains relatively unexplored. ...
Positive-Unlabeled (PU) Learning is a challenge presented by binary classification problems where there is an abundance of unlabeled data along with a small number of positive data instances, which can be used to address chronic disease screening problem. State-of-the-art PU learning methods have resulted in the development of various risk estimators, yet they neglect the differences among distinct populations. To address this issue, we present a novel Positive-Unlabeled Learning Tree (PUtree) algorithm. PUtree is designed to take into account communities such as different age or income brackets, in tasks of chronic disease prediction. We propose a novel approach for binary decision-making, which hierarchically builds community-based PU models and then aggregates their deliverables. Our method can explicate each PU model on the tree for the optimized non-leaf PU node splitting. Furthermore, a mask-recovery data augmentation strategy enables sufficient training of the model in individual communities. Additionally, the proposed approach includes an adversarial PU risk estimator to capture hierarchical PU-relationships, and a model fusion network that integrates data from each tree path, resulting in robust binary classification results. We demonstrate the superior performance of PUtree as well as its variants on two benchmarks and a new diabetes-prediction dataset.
... • Web-Based DSS delivers decision-support information and provides decision support tools to a manager or business analyst using a "thin-client" web browser. As an example, web-based DSS named "Movie Forecast Guru" is developed to assist the decision-making process of the holly wood managers in the motion picture industry [16] Notably, data-driven DSSs and knowledge-driven DSSs are interrelated. Data analysis is a step-bystep process performed by collecting data, understanding, cleaning, transforming, and modeling data to extract useful information that supports the decision-making process of the expert. ...
The weather observation and forecasting systems have become vital to every country for improving the efficiency of several systems that deal with life and property. Over the years, the weather information and forewarning systems are gradually becoming powerful, domain-specific, and location-specific.
Weather-based decision support systems (DSSs) are being built to improve the efficiency of healthcare delivery, agricultural production systems, transportation sector, governance systems, and so on.
In weather based DSS, given a weather situation, the domain experts prepare the appropriate suggestions to improve the efficiency of the stakeholders for carrying out day-to-day operations. Once the domain experts prepare a suggestion for a given weather situation, there is a scope to reuse the same suggestion
for the similar weather situations in the future. As a result, the performance of the weather-based DSS could be improved. Notably, the notion of reuse is widely applied to improve the performance of DSSs in multiple domains. For example, the notion of reuse is widely applied to reduce the software development cost in the software domain. Notably, in the literature, the concept of reuse is not being explored to improve the performance of weather-based DSS.
In this thesis, we introduced the problem context and proposed two frameworks to improve reuse in weather-based DSSs. As a part of the problem context, we defined two notions, viz. weather condition (WC) and coupled WC, to capture two types of weather situations. Moreover, we have defined the notions of cycle, period, temporal reuse, spatial reuse and coverage percentage metric.
As the first approach, we proposed a framework to improve reuse by proposing the notion of Categorybased WC (CWC). The basic idea is that it is possible to improve the performance of weather-based DSS by exploiting the weather-based categories of the given domain. By considering the weather categories provided by India Meteorological Department (IMD), we have analyzed the extent of temporal reuse
among the daily and five-day CWCs by conducting extensive experiments on 30 years of weather data collected at Rajendranagar, Hyderabad, Telangana, India. By varying the number of weather variables in CWC from one to five, we have computed the extent of temporal reuse among one-day and five-day
CWCs for the following period types: year, season, and phenophases (i.e., growth stages) of the Rice crop. The results show that it is possible to improve reuse significantly with the proposed framework.
The results also show that by preparing agro advisories for the first two years, there is a scope to achieve about 80 percent reuse in the third year for all period types.
We have also conducted experiments to analyze both temporal reuse and spatial reuse among the CWCs by considering weather data of 12 locations (blocks) in the Telangana state. The results show that it is possible to improve reuse significantly by combining both temporal and spatial reuse. Moreover, we have also conducted validation experiments of the proposed framework by analyzing the similarity
among the corresponding real weather-based text advisories during 2016 to 2019. The results show that the proposed framework is exhibiting encouraging results.
As the second approach, we presented a framework to improve reuse by proposing the notion of Category-based Coupled WC (CCC). We have analyzed the extent of temporal reuse among the CCC by conducting extensive experiments on 30 years of weather data collected at Rajendranagar, Hyderabad, Telangana, India. By varying the number of weather variables in CCC from one to five, we have
computed the extent of temporal reuse among one-day and five-day CCCs for the following period types: year, season, and phenophases (i.e., growth stages) of the Rice crop. The results show that by preparing agro advisories for the first two years, there is a scope to achieve about 60 percent reuse in the third year for all period types. For the agriculture domain, the results provide an opportunity to improve the efficiency of weather-based DSSs by improving the reuse of the weather-based suggestions. The proposed framework is generic and can be applied to any weather-based DSS of any given domain. For any domain, the DSS
developed under the proposed framework has a potential to reduce the repetition of the work, minimize operational costs and improve the quality of weather-based suggestions.
... References [4,9] sought to design the box office trend on a timeline, for instance, a paradigm of the Bass diffusion model. Classification and regression tree (CART) [8], Artificial Neural Network (ANN) [10,21,38] were implemented under machine learning-based. Algorithms mentioned above produced unsatisfactory forecasting results due to the lack of variable diversity and their simplicity of forecasting, and little attention to approaching these subjects systematically from a design point of view. ...
Demand forecasting a film’s opening weekend box office revenue is a difficult and complex task that decision-makers face due to a lack of historical data and various complex factors. We proposed a novel Deep Multimodal Feature Classifier Neural Network model (DMFCNN) for predicting a film’s opening weekend box office revenue using deep multimodal visual features extracted from movie posters and movie metadata. DMFCNN is an end-to-end predictive model that fuses two different feature classifiers’ predictive power in estimating the movie box office revenue. Initially, a pre-trained residual convolutional neural network (ResNet50) architecture using transfer learning techniques extracts visual, and object representations learned from movie posters. The movie posters’ discriminative and financial success-related features are combined with other movie metadata to classify the movie box office revenue. The proposed DMFCNN aided in developing a robust predictive model that jointly learns and defines useful revenue-related poster features and objects semantics, which strongly correlates with movie box office revenue and aesthetic appearance. Although our main task was classification, we also analyzed regressions between our exogenous variables as a regularizer to avoid the risk of overfitting. We evaluated DMFCNN’s performance and compared it to various state-of-the-art models on the Internet Movie Database by collecting 49,857 movies metadata and posters from 2006 to 2019. The learned information on movie posters and predicted outcomes outperformed existing models, achieving 59.30% prediction accuracy. The proposed fusion strategy outperformed the existing fusion schemes in precision, Area Under Cover, sensitivity, and specificity by achieving 80%, 81%, 79%, and 78%, respectively.
... To resolve this problem for hiring managers, we propose an automated decision support tool that can be used to identify high probability candidates of absenteeism at an early stage in the recruitment process. For example, Delen et al. (2007) developed an automated web-based tool integrating prediction models to provide Hollywood producers with a way to classify a movie in one of nine success categories, ranging from flops to blockbusters. Simsek et al. (2020) have developed an automated tool that uses artificial neural networks (ANN) to identify point velocity profiles on rivers with an accuracy level of 0.46. Figure 1 provides an overview of how the web-based interactive tool was developed and how it can be utilized. ...
Purpose - Inefficient hiring may result in lower productivity and higher training costs. Productivity losses caused by absenteeism at work cost U.S. employers billions of dollars each year. Also, employers typically spend a considerable amount of time managing employees who perform poorly. The purpose of this study is to develop a decision support tool to predict absenteeism among potential employees. Design/methodology/approach - We utilized a popular open-access dataset. In order to categorize absenteeism classes, the data have been preprocessed, and four methods of machine learning classification have been applied: Multinomial Logistic Regression (MLR), Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Random Forests (RF). We selected the best model, based on several validation scores, and compared its performance against the existing model; we then integrated the best model into our proposed web-based for hiring managers. Findings - A web-based decision tool allows hiring managers to make more informed decisions before hiring a potential employee, thus reducing time, financial loss and reducing the probability of economic insolvency. Originality/value - In this paper, we propose a model that is trained based on attributes that can be collected during the hiring process. Furthermore, hiring managers may lack experience in machine learning or do not have the time to spend developing machine learning algorithms. Thus, we propose a web-based interactive tool that can be used without prior knowledge of machine learning algorithms.
... Information fusion can be used to combine the results from different predictive models. Following formula has been used (Delen et al., 2007(Delen et al., , 2012Oztekin, 2012;Oztekin et al., 2013) to measure sensitivity of the independent variable x k by infusing information from n prediction models. where i refers to the normalised weight value according to the predictive power of the i th prediction model and S ik is the sensitivity measure for the independent variable x k in the i th prediction model. ...
... These studies can be categorized into two groups [39,35]: (i) proposal of a new forecasting algorithm or resolution of issues in existing algorithms; (ii) determination of explanatory variables for more accurate box-office forecasting. With regard to the forecasting algorithm development, extant studies can be divided into three subgroups: [1] statistical learning algorithms such as multiple linear regression [20,10,62,51] and probabilistic algorithms such as the hierarchical Bayesian model [2,2] time-series forecasting algorithms such as the product diffusion model [17,70,44,7,3] machine-learning-based algorithms such as classification and regression tree (CART) [16,43], artificial neural network (ANN) [29,64,78], and BP neural network [80]. From the perspective of explanatory variable configuration, the main topic has been how to integrate movie characteristics and WOM into explanatory variables. ...
This study aimed to develop a new diffusion model for box-office forecasting by modifying the generalized Bass diffusion model with incorporation of search trend data and historical movie-audience data. To that end, first, movie-audience data (i.e., the number of moviegoers) and NAVER search trend data for each of the top 30 movies released in Korea in 2018 were collected by day. Then, the modified generalized Bass diffusion model, newly proposed in this paper, was applied in order to estimate the diffusion parameters. The results of our empirical case study on the Korean film market show that NAVER search trend data plays an important role in box-office forecasting after a movie is released. This study contributes to the extant literature by proposing a new diffusion model, which is a novel online big-data-driven methodology of box-office forecasting. In addition, comparison analysis with two other representative diffusion models was conducted, and the proposed model showed superior prediction power.
... Information fusion can be used to combine the results from different predictive models. Following formula has been used (Delen et al., 2007(Delen et al., , 2012Oztekin, 2012;Oztekin et al., 2013) to measure sensitivity of the independent variable x k by infusing information from n prediction models. where i refers to the normalised weight value according to the predictive power of the i th prediction model and S ik is the sensitivity measure for the independent variable x k in the i th prediction model. ...
... Deep SHAP has a solid theoretical foundation in the game theory and provides a trustworthy explanation because its prediction is fairly distributed among the input variables. (4) Using Eq.3, the importance value of each product attribute is estimated based on the information fusion algorithm [42] for combining deep SHAP values in k optimal neural networks. The importance value is finally normalized by Eq. 4: ...
Importance-performance analysis (IPA) is a technique used to understand customer satisfaction and improve the quality of product attributes. This study proposes an explainable deep-neural-network-based method to carry out IPA of product attributes from online reviews for product design. Previous works used shallow neural network (SNN)-based methods to estimate importance values, but it was unclear whether the SNN is an optimal neural network architecture. The estimated importance has high variability by a single neural network from a training set that is randomly selected. However, the proposed method provides importance values with a lower variance by improving the importance estimation of each product attribute in the IPA. The proposed method first identifies the product attributes and estimates their performance. Then, it infers the importance values by combining explanations of the input features from multiple optimal neural networks. A case study on smartphones is used herein to demonstrate the proposed method.
... While there exist complicated issues in the unpredictable nature of box office prediction, several researchers have suggested models primarily utilizing statistics-based forecasting approaches or machine learning approaches like multi-layer perceptron neural networks to suggest the solutions for forecasting box office [6]. For instance, Delen et al. [41] suggested forecasting models for motion picture success by using discriminant analysis, decision trees, and artificial neural network to determine the class of the box office size. While box office prediction is a forecasting problem for real values, this has often been considered as a classification problem which forecasts to show whether a specific movie can show greater revenue than a certain extent [36]. ...
The studies are almost nonexistent regarding production efficiency of movies which is determined based on the relationship between movie resources powers (powers of actors, directors, distributors, and production companies) and box office. Our study attempts to examine how efficiency moderates the relationship between eWOM (online word-of-mouth) and revenue, and to show the difference in prediction performance between efficient and inefficient movies. Using data envelopment analysis to suggest efficiency of movies, movie efficiency negatively moderates the effects of review depth and volume on subsequent box office revenue compensating negative effects of smaller box office in previous period while efficiency exert a positive moderating effect on the influences of review rating and the number of positive reviews on revenue. This shows that review depth and volume are affected by the slack of movie resources powers for inefficient movies, and high rating and positive response for efficient movies to affect revenue. The results of decision trees, k-nearest-neighbors, and linear regression analysis based on ensemble methods using eWOM or movie variables indicate that the movies with the inefficient movie resources powers are providing greater prediction performance than movies with efficient movie resources powers. This show that diverse variation in the efficiency of movie resources powers contributes to prediction performance.
... Given the number of data is not such sufficient and the large number of variables, we focus on other non-deep learning methods such as decision trees and k-NN besides neural networks. Decision support systems (DSS) used to support complex decision-making and problem solving tasks using business Intelligence systems (Delen et al., 2007). As a decision support method based on business intelligence, decision trees and k-NN have been well utilized in box office prediction (Kim et al., 2015;Liu et al., 2016;Zhou et al., 2019) Based on these widely used methods, we proposed ensemble methods in order to investigate the effectiveness of ensemble methods. ...
While many business intelligence methods have been applied to predict movie box office revenue, the studies using an ensemble approach to predict box office revenue are almost nonexistent. In this study, we propose decision trees, k-nearest-neighbors (k-NN), and linear regression using ensemble methods and the prediction performance of decision trees based on random forests, bagging and boosting are compared with that of k-NN and linear regression based on bagging and boosting using the sample of 1439 movies. The results indicate that ensemble methods based on decision trees (random forests, bagging, boosting) outperform ensemble methods based on k-NN (bagging, boosting) in predicting box office at week 1, 2, 3 after release. Decision trees using ensemble methods provide better prediction performance than ensemble methods based on linear regression analysis in the box office at week 1 after release. This is explained by the results that after comparing the prediction performance between ensemble methods and non-ensemble methods. For decision tree methods, unlike the other methods, the prediction performance of ensemble methods is greater than that of non-ensemble methods. This shows that decision trees using ensemble methods provide better application effectiveness of ensemble methods than k-NN and linear regression analysis.
... In a nutshell, this area of research, initially rooted in human resources, has revealed that successful applications of talent analytics are becoming a new source of competitive advantage (Chamorro-Premuzic 2016; Davenport et al. 2010). It has also given rise to the concept of "star power," which is among the most widely considered antecedents of box office success (Delen et al. 2007;Elberse 2007;Hur et al. 2016;Kim et al. 2015;Liu et al. 2014;Marshall et al. 2013). ...
Producing compelling film content profitably is a top priority to the long-term prosperity of the film industry. Advances in digital technologies, increasing availabilities of granular big data, rapid diffusion of analytic techniques, and intensified competition from user-generated content and original content produced by subscription video on demand platforms have created unparalleled needs and opportunities for film producers to leverage analytics in content production. Built upon the theories of value creation and film production, this article proposes a conceptual framework of key analytic techniques that film producers may engage throughout the production process, such as script analytics, talent analytics, and audience analytics. The article further synthesizes the state-of-the-art research on and applications of these analytics, discuss the prospect of leveraging analytics in film production, and suggest fruitful avenues for future research with important managerial implications.
... In 2005, Delen and Sharda [4] implemented a system called Forecast Guru, which was a decision support system for Hollywood managers. It employed various techniques and merged their results afterward. ...
Recent progress in machine learning and related fields like recommender systems open up new possibilities for data-driven approaches. One example is the prediction of a movie's box office revenue, which is highly relevant for optimizing production and marketing. We use individual recommendations and user-based forecast models in a system that forecasts revenue and additionally provides actionable insights for industry professionals. In contrast to most existing models that completely neglect user preferences, our approach allows us to model the most important source for movie success: moviegoer taste and behavior. We divide the problem into three distinct stages: (i) we use matrix factorization recommenders to model each user's taste, (ii) we then predict the individual consumption behavior, and (iii) eventually aggregate users to predict the box office result. We compare our approach to the current industry standard and show that the inclusion of user rating data reduces the error by a factor of 2x and outperforms recently published research.
... While most econometric studies dealt with explaining a continuous measure of movie success (such as box office sales), the authors of most recent studies on using data mining techniques for movie forecasting tend to use discrete measures of movie success (Delen et al 2007;Lee and Chang, 2009;Sharda and Delen, 2006). However, it may often be not very useful to predict the revenue range, because ordinal response modeling gives practically no opportunity to estimate the expected return on investment. ...
In this study we develop a model for early box office receipts forecasting that, in addition to traditionally used regressors, uses several inputs that have never been used before, but appeared to be very useful predictors according to our variable importance analysis. New predictors account for the power of actors and directors, as well as for the intensity of competition at the time of movie release. Instead of Motion Picture of Association of America (MPAA) ratings commonly used in movie success prediction, textual information about the reasons for giving a movie its MPAA rating was formalized using word frequency and principal components analyses. The expert system is based on the Random forest algorithm, which outperformed a stepwise regression and a multilayer perceptron neural network. A regression tree-based diagnostic approach allowed us to detect the heterogeneity of model accuracy across segments of data and assess the applicability of the model to different movie types.
... geliştirilmesinde risk analizi yapan bulanık küme teorisi kullanan bir web tabanlı karar destek sistemi geliştirmiştir.Ray (2007) web tabanlı karar destek teknolojilerinin gerçekleştirimini gösteren bir durum çalışması yapmıştır.Chen et al.(2007) web tabanlı grup karar destek sistemlerinin tasarımı, uygulanması ve değerlendirilmesini incelemiştir.Delen et al. (2007) sinema endüstrisindeki karar vericilere yardımcı olmak için web tabanlı karar destek sistemi geliştirmişlerdir. ...
Bu tezde, günlük hayatta karşılaşılan karmaşık karar problemlerinin optimal olarak çözülebilmesi için melez zeki karar destek sistemlerinin geliştirilmesi ve uygulanması konusu araştırılmıştır. Karar problemleri genel olarak birden fazla kriter içerir ve çok kriterli karar verme (ÇKKV) algoritmaları kullanılarak çözülebilmektedir fakat bu problemler çoğu zaman belirsiz ve doğrusal olmayan özellikler içermektedir. Bu tür belirsizlik içeren durumlarda doğrusal olmayan özelliklerin modellenmesi için ÇKKV yöntemleri yetersiz kalmakta ve bulanık mantık, bulanık çıkarım ve yapay sinir ağları gibi yapay zeka tekniklerine ihtiyaç duyulmaktadır. Karar destek sistemleri (KDS) ise belirsizlik seviyesi yüksek olan bu tür karar problemlerini çözmek için analitik modeller kullanarak karar vericiye kolaylık sağlarlar.Çalışmada melez zeki karar destek sistemlerinin tasarımı ve gerçekleştirimi için genel bir karar destek modeli önerilmiştir. İki farklı karmaşık karar problemi için ÇKKV ile yapay zeka tekniklerinin melez olarak birlikte kullanımı incelenmiş ve problemlerin çözümüne yönelik karar destek sistemleri geliştirilmiştir. Daha sonra geliştirilen melez zeki karar destek sistemlerinin gerçekleştirimi yapılmıştır. Sistem mimarileri ve deneysel sonuçlar örnekler üzerinde açıklanmıştır. Geliştirilen karar destek sistemlerinin iyileştirilmesi için yapılabilecekler ve diğer karar problemlerine nasıl uyarlanabileceği tartışılmıştır.
ENGLISH:
In this thesis, developing and performing hybrid intelligent decision support systems has been studied to obtain optimal solution for the complex decision problems in daily life. Decision problems usually include more than one criterion and they can be solved using multi criteria decision making (MCDM) algorithms, however, these problems usually contain non-linear and uncertain attributes. In such undetermined cases, MCDM techniques are insufficient to model non-linear attributes therefore artificial intelligence techniques such as fuzzy logic, fuzzy inference and artificial neural networks are required. Decision Support Systems (DSS) provide simplicity using analytical models for decision makers to solve decision problems which have high uncertainty level.In this study; a general decision support model has been proposed to design and implement hybrid intelligent decision support systems. Usage of MCDM and artificial intelligence techniques together has been examined for two different decision problems and decision support systems have been developed to solve these problems. Then implementation of developed hybrid intelligent decision support systems has been performed. System architectures and experimental results with illustrative examples are demonstrated. There is some important discussion on how the developed decision support systems can be improved and how they can be applied to other decision problems.
... They include ads expenditure [18,25,63], prerelease piracy [12,13,42], reviews and ratings [6,7,11,15,16,20,32,39], prerelease search activities [35], the number of concurrent movie showings [2], political views of the moviegoers [53], Wikipedia status [44], and Hollywood Stock Exchange [18,55]. Delen et al. [14] have devised a web-based decision support system to make forecast on box office sales. The system incorporates many of the measurements mentioned. ...
The mainstream research of social factors and box office performance has concentrated on post-consumption opinion mining and sentiment analysis, which are difficult to operationalize to the benefits of the industry practitioners whose objective is to maximize box office sales. In this study, we propose the Facebook "like" as an effective social marketing tool before the release of movies for several reasons. Firstly, people's prerelease "liking" of movies can be influenced by marketing campaigns. Secondly, the clicks of "likes" create social impact, as suggested by the Social Impact Theory, on moviegoers' consumption behaviors. And thirdly, Facebook "like" provides practitioners with real-time visible updates. By studying the impact of prerelease "likes" on box office sales, we not only contribute to the literature by offering a new social metric to evaluate the box office performance, but also provide the industry practitioners with quantitative support for the effectiveness of their social marketing activities. Our empirical results indicate that the prerelease "likes" exert a significantly positive impact on box office performance. More specifically, 1% increase in the number of "likes" in the one week prior to release is associated with an increase of the opening week box office by about 0.2%. As it approaches the release date, the prerelease "like" impact becomes stronger, suggesting that the latest prerelease "likes" are more effective in driving box office performance.
... There is a consensus that such a fusion produces more useful information in knowledge discovery in database practices (Batchelor and Dua, 1995;Chase, 2000). The information fusion algorithm can be formulated as in the following equation where the output (dependent) variable is shown by variable y and the input (independent) variables by x 1 , x 2 , …, x n (Delen et al., 2007): ...
Purpose
The prediction of graduation rates of college students has become increasingly important to colleges and universities across the USA and the world. Graduation rates, also referred to as completion rates, directly impact university rankings and represent a measurement of institutional performance and student success. In recent years, there has been a concerted effort by federal and state governments to increase the transparency and accountability of institutions, making “graduation rates” an important and challenging university goal. In line with this, the main purpose of this paper is to propose a hybrid data analytic approach which can be flexibly implemented not only in the USA but also at various colleges across the world which would help predict the graduation status of undergraduate students due to its generic nature. It is also aimed at providing a means of determining and ranking the critical factors of graduation status.
Design/methodology/approach
This study focuses on developing a novel hybrid data analytic approach to predict the degree completion of undergraduate students at a four-year public university in the USA. Via the deployment of the proposed methodology, the data were analyzed using three popular data mining classifications methods (i.e. decision trees, artificial neural networks, and support vector machines) to develop predictive degree completion models. Finally, a sensitivity analysis is performed to identify the relative importance of each predictor factor driving the graduation.
Findings
The sensitivity analysis of the most critical factors in predicting graduation rates is determined to be fall-term grade-point average, housing status (on campus or commuter), and which high school the student attended. The least influential factors of graduation status are ethnicity, whether or not a student had work study, and whether or not a student applied for financial aid. All three data analytic models yielded high accuracies ranging from 71.56 to 77.61 percent, which validates the proposed model.
Originality/value
This study presents uniqueness in that it presents an unbiased means of determining the driving factors of college graduation status with a flexible and powerful hybrid methodology to be implemented at other similar decision-making settings.
... Therefore, there is an increasing deployment of IF techniques in data-mining problems as opposed to the application of a single method [12,46]. In our study, we adopt the information fusion model presented by Delen et al. [47] since it has provided us with good performance in the pilot analysis and it can be easily explained to medical practitioners. ...
Recent research has shown that data mining models can accurately predict the outcome of a heart transplant based on predictors that include patient and donor's health/demographics. These models have not been adopted in practice, however, since they did not: a) consider the interactions between the explanatory variables; b) provide a patient's specific risk of survival (reported results have been primarily deterministic); and c) offer an automated decision tool that can provide some data-driven insights to practitioners. In this study, we attempt to overcome these three limitations through the use of Bayesian Belief Networks (BBN). The proposed BBN framework is comprised of four phases. In the first two phases, the data is preprocessed, and a candidate set of predictors is generated based on employing several variable selection methods. The third phase involves the addition of medically relevant variables to the list. In phase four, the BBN model is applied. The results show that the proposed BBN method provides similar predictive performance to the best approaches in the literature. More importantly, our method provides novel information on the interactions among the predictors and the conditional probability of survival for a given set of relevant donor–recipient characteristics. We offer U.S. practitioners a decision support tool that presents an individualized survival score based on our BBN model (and the UNOS dataset).
... Thus, the next stage in the DSS progression is the Web-based DSS, which delivers appropriate data and models to a manager or a decision maker using a thin-client Web browser [Power and Kaparthi 2002;Liou et al. 2007]. Using Web-based DSS, organizations can provide DSS capability to managers over a proprietary intranet, to customers and suppliers over an extranet, or to any stakeholder over the Internet [Sikder and Gangopadhyay 2004;Delen and Sharda 2007]. Bhargava and Power [2001] provide a status report on how Web technologies are being used to provide decision-support services over the Internet. ...
... As a result, numerous development of DSS application through web platform has been done in several of field. For instance, a web-based DSS for movie forecast [24], a web based DSS with GIS technology for resources and environment management [25], a web based DSS for railway operation [26], and a web based DSS for construction and demolition waste [27]. ...
The emerging of new Information Communication Technology (ICT) technology namely Building Information Modeling been proven benefits toward construction industry. As a result, the list of BIM software available in the market is keep increasing in recent years. This has led to the selection problem among construction companies. Moreover, the selection BIM software also required high investment in term of software, hard ware and training expenses. These aforementioned issues have increased the complexities of decision process and the need of decision aid in BIM software selection. Thus, this paper has introduced a new approach in MCDMDSS web development by utilization of Web 2.0 application. The rapid development of Information technology has highly benefit to the development of web based DSS. The design and validation architecture of a web base DSS called topsis4BIM for Building Information Modeling (BIM) is presented.
The Random Forest algorithm (RFA) is used to predict the approximate final box-office revenue of a movie in the Taiwanese film market. The results show that the RFA has stable capabilities to predict the final box-office revenue of a movie during its theatrical period with an 80% overall accuracy. Two other machine learning algorithms, i.e., the Support Vector Machine and the Logistic Regression algorithms, are applied for comparison with the RFA. We find that the RFA still achieves the highest overall accuracy of prediction in our experiment. Additionally, we applied an unsupervised machine learning method to distinguish each group in the box office revenue categories in the classification problem. Also, the feature importance analysis indicates that word-of-mouth plays a vital role in theatrical revenue determination. Our findings imply several crucial suggestions for film distributors.
The over-the-top (OTT) industry has witnessed remarkable growth in recent years with a sharp increase in the number of subscribers, leading to increased competition among OTT platforms to acquire movie rights. Consequently, the gap between the theatrical and OTT releases has been diminishing over the last few years. An early release of a movie on an OTT platform fetches a higher distribution fee for a movie distributor (MD), however, it reduces the MD’s revenue from the theatrical release. Therefore, it becomes critical for the MD to determine the optimal release time and distribution fee combination. In this paper, we analytically solve the MD’s decision problem and provide a detailed analysis of how the optimal release time varies with changes in platform characteristics such as the proportion of ad revenue and the platform’s risk profile, movie characteristics such as success factor and suitability for OTT, and market characteristics such as broadband penetration, piracy rate and customers’ preferences for viewing channels. We compare our results with the actual release times of 243 movies released during 2015–2022. We find that the optimal release time increases with ad revenue proportion, broadband penetration, and piracy rate, whereas the optimal fee reduces non-linearly with release time and depends on OTT’s risk profile. Our findings also indicate that the optimal release time reduces for movies that do not provide any additional utility for theater goers, and as customers’ preference towards OTT increases. Our work provides much-needed guidelines for professionals dealing with movie releases on OTTs.
Reduction of maternal and infant mortality rates has been recognisedas one of the important goals of this century. Both coverageimprovement and inequity reduction have been set up asmillennium targets. Despite the availability of effective interventions,maternal and child healthcare conditions are not improvingin developing countries because of inefficiently functioninghealth systems. Knowledge generation about behaviors ofhealth system building blocks on the implementation of severalhealthcare interventions will help policymakers to design situation-specific and strategic interventions. A decision supportsystem has been devised incorporating data mining algorithmswhich would help to understand the condition of maternal andchild healthcare indicators; educational, socio, and economicsituations; healthcare status; and healthcare service blocksand their relationships with each other. In this paper, the designof the DSS has been discussed elaborately. To enhance a system-wide understanding of the healthcare system, all healthcare-related factors have been incorporated into this system.Three knowledge generation modules have been prepared byutilizing different visualization and data mining algorithms.
In the recent past, machine learning paradigms like the ensemble approaches have been used effectively to predict revenue from large volumes of sales data that helped the decision-making process in many businesses. The proposed work in this paper proposes a modified approach of ensemble algorithms to predict box office revenues of upcoming movies. A shallow version of the gradient boosting (XGBoosts) has been proposed to predict the box office revenue of movies based on several primary and derived features related to the movies in particular. Further studies have found that features such as budget, runtime, budget year ratio can also be considered as some of the more important estimators of the box office revenue. These features along with some other features have been used as an input to the proposed model in this proposed work to make significantly good predictions about the box office collection of a movie. The results are reported by testing and forecasting based on simulation on a standard data set. The precision of the model is tested using popular metrics such as R2, MSLE. The results reported gives efficacy of the proposed approach that can be further used in other business models words.
Participation in SIWES since its inception has become a necessary precondition for the award certificates in specific disciplines especially Engineering, Sciences and other Technology related disciplines in most tertiary institutions across Nigeria, in accordance with the education policy of government. Nigeria has about 200 tertiary institutions which include Universities, Polytechnics and college of educations. With over 200 tertiary institutions (Universities, Polytechnics and College of Educations) across the country operating on different academic calendar, the number of students that participate in SIWES from Universities, Polytechnics and Colleges of Education is within the range of 15000 to 25000 yearly for a minimum of 4 to 6 month; the ITF is task with managing and maintaining the record. For such reasons, most of the ITF area offices across the 36 states of the country and SIWES offices in the institutions all over the country have a collection of manual files and registers to store record of student embarking on the skill acquisition exercise from these institutions across the country every year. The existing system is characterised by manual approach of record keeping, and feature an inappropriate flow of information within the separate unit of the ITF. Students are issued with SIWES Letter of introduction from their department, which is obtained. Students submit acceptance letters obtained from their proposed area of industrial attachment and are issued with a form to record their bank account details and form 8 which usually comes after students have gone on industrial training. The weakness of the existing system, are: Delay in flow of information between various units involve in SIWES coordination. Presence of redundant information. Procedure of obtaining SIWES forms is stressful. The procedure of managing student's record is prone to error. The proposed system was developed to run on a remote server using web technology and will be accessed by the users using a web browser such as Mozilla, Opera, and Chrome or internet explorer. The new system will feature a friendly graphical user interface for interacting with the users; the system will feature a security subsystem that will be used to authenticate user requesting access into the system. The proposed system have 5 different types of interface for interacting with the system each of which grants specific access right to the operations the users can perform. They are Student interface, Departmental interface, Institution interface, State area office interface and national interface. The implementation of this system requires the use of web technology and web development language in particular PHP. The front-end of the system is development using basically HTML, CSS and JavaScript while at the back-end, PHP for server interaction and MySQL is used for the data structure.
The academic performance of a higher education student can be affected by several factors and in most cases Higher Education Institutions (HEI) have programs to intervene, prevent failure or students dropping out. These include student tutoring, mentoring, recovery classes, summer school, etc. Being able to identify the borderline cases is extremely important for planning and intervening in time. This position paper reports on an ongoing project, being developed at the University of Trás-os-Montes e Alto Douro (UTAD), which uses the students’ data and artificial intelligence algorithms to create models and predict the performance of students and classes. The main objective of the IA.EDU project is to research the usage of data, artificial intelligence and data science to create artificial intelligence solutions, including models and applications, to provide predictive information that can contribute to the increase in students’ academic success and a reduction in the dropout rate, by making it possible to act proactively with the students at risk, course directors and course designers.
Marketing activity by distributors is a significant factor in attracting audiences to theaters before a movie is released. Importantly, audience numbers on opening weekend are highly affected by marketing activity before the release, and these numbers determine how many screens will be allocated to the movie. Therefore, distributors need to predict audience numbers on opening weekend and develop marketing strategies in order to gain a competitive advantage over other films being screened at the same time. However, as distributors make predictions based on their experiences and intuitions, it is difficult to quantify the reliability of predicted values and deliver the correct marketing strategy. In this study, we propose a model that predicts audience numbers on the opening Saturday using market research data obtained through online and offline surveys to help distributors develop better marketing strategies.
The purpose of this paper is to study decision support systems where information systems have become important to support the decision-making process in organizations and create an appropriate environment that has become more complex. The main objective of decision support systems is to develop techniques to support decision-making and use in all areas and organizations. The information age, rapid information dissemination and increased data flow have increased the competitive environment among organizations, so the use of decision support systems has become important for enterprises to increase their ability to adapt to the environment by making appropriate decisions accurately by relying on the Internet based on support systems. The study also demonstrated DSS components and types and Web impact on decision support systems, system features, and decision support across the web, comparison of traditional decision support systems and web-based decision support systems and advantages of web-based support systems. Decision support systems in organizations whose decision-making has become critical to the organizations' success, continuity or failure.-
The purpose of this paper is to study decision support systems where information systems have become important to support the decision-making process in organizations and create an appropriate environment that has become more complex. The main objective of decision support systems is to develop techniques to support decision-making and use in all areas and organizations. The information age, rapid information dissemination and increased data flow have increased the competitive environment among organizations, so the use of decision support systems has become important for enterprises to increase their ability to adapt to the environment by making appropriate decisions accurately by relying on the Internet based on support systems. The study also demonstrated DSS components and types and Web impact on decision support systems, system features, and decision support across the web, comparison of traditional decision support systems and web-based decision support systems and advantages of web-based support systems. Decision support systems in organizations whose decision-making has become critical to the organizations' success, continuity or failure.-
Rapid advancements have been made in the field of artificial intelligence in recent years. This has resulted in its adoption in various technologies from medicine to search engines. Existing media management systems have however not yet fully leveraged the power of artificial intelligence (AI) to give users enhanced information apart from basic media metadata. This chapter proposes a smart movie management system which works majorly offline and uses AI to deliver optimum information to the users on four vital tasks. These tasks are multilevel phrase level review polarity, plot and review keywords, a content-based recommendation system, and an emotion recognition system. The complete system works in near-real time with a user-friendly presentation to maximize a user's information gain.
Performing arts and movies have become commercial products with high profit and great market potential. Previous research works have developed comprehensive models to forecast the demand for movies. However, they did not pay enough attention to the decision support for performing arts which is a special category unlike movies. For performing arts with high-dimensional categorical attributes and limit samples, determining ticket prices in different levels is still a challenge job faced by the producers and distributors. In terms of these difficulties, factorization machine (FM), which can handle huge sparse categorical attributes, is used in this work first. Adaptive stochastic gradient descent (ASGD) and Markov chain Monte Carlo (MCMC) are both explored to estimate the model parameters of FM. FM with ASGD (FM-ASGD) and FM with MCMC (FM-MCMC) both can achieve a better prediction accuracy, compared with a traditional algorithm. In addition, the multi-output model is proposed to determine the price in multiple price levels simultaneously, which avoids the trouble of the models’ repeating training. The results also confirm the prediction accuracy of the multi-output model, compared with those from the general single-output model. © 2018, Shanghai Jiaotong University and Springer-Verlag GmbH Germany, part of Springer Nature.
Box-office forecasting is a challenging but important task for movie distributors in their decision making process. Many previous studies have tried to determine a way to accurately predict the box-office, but the results reported have not been satisfactory for two main reasons: (1) lack of variable diversity and (2) simplicity of forecasting algorithms. Although the importance of word-of-mouth (WOM) has consistently emphasized in past studies, only summarized information, such as volume or valence of user ratings is commonly used. In forecasting algorithms, multiple linear regression is the most popular algorithm because it generates not only predicted values but also variable significances. In this study, new box-office forecasting models are presented to enhance the forecasting accuracy by utilizing review sentiments and employing non-linear machine learning algorithms. Viewer sentiments from review texts are used as input variables in addition to conventional predictors, whereas three machine learning-based algorithms, i.e., classification and regression tree (CART), artificial neural network (ANN), and support vector regression (SVR), are employed to capture non-linear relationship between the box-office and its predictors. In order to provide variable importance for machine learning-based forecasting algorithms, an independent subspace method (ISM) is applied. Forecasting results from six different forecasting periods show that the presented methods can make accurate and robust forecasts.
The rapid development of Web technology has opened a new approach to Decision Support System (DSS) development. For instance, Social Media is one of the Web 2.0 digital platforms that allow the creation and exchanges of user-generate content through an interactive interface, high user control and mass participation. The concept and characteristics of Web 2.0 such as remote, platform-independent, context-rich and easy to use, which is fulfill the concept and purpose of DSS. This paper outlines some of the elementary concepts of Web 2.0 and social media technology which can be potentially integrated within DSS to enhance the decision-making process. Our initial investigation indicates that there is limited study attempt to embed Web 2.0 into DSS. Thus, this paper highlights the importance of Web 2.0 technology in order to foster the betterment of DSS development and its usability.
The rural financial organization plays an important role in promoting the healthy development of the national economy especially the development of the rural economy. However, the rural financial organization risk especially the operating risk is still an outstanding problem. It has become a big obstacle in new countryside development. In this paper we analyzes the rural financial organization operational risk index firstly, then use these index as the input data for the BP neural network. After that we modeling rural financial organization operational risk early warning based the BP neural network. At last we take an experiment on a rural somewhere, the result shows that the BP neural network can reflect of the operation risk of the rural financial organization quickly and accurately.
Most business students in universities across the United States find the quantitatively oriented courses challenging to comprehend the course material to a degree necessary to develop capability and confidence level to solve business problems. A determination of critical factors that influence performance in such courses is critical to designing class instructions. Instructors teaching these classes agonize over the fact that these courses are amongst the most difficult to teach as they encompass relatively harder concepts transformed into analytical skill sets with real applications to business operations that students struggle to grasp. This study employs a machine learning-based approach to determine critical success factors by analyzing the dataset of a focus course and provides some guidelines to educators for improving their teaching effectiveness. Information fusionbased sensitivity analyses on the data mining models provide an unbiased weighting scheme for the rank order of the variables that help predict the students' comprehension level.
A study developed and validated new scales for perceived usefulness and perceived ease of use, which were hypothesized to be fundamental determinants of user acceptance. The definitions of the 2 variables were used to develop scale items that were pretested for content validity. The items were then tested for reliability and construct validity in 2 studies involving a total of 152 users and 4 application programs. After refining and streamlining the measures, the resulting 2 scales of 6 items each demonstrated reliabilities of .98 for usefulness and .94 for ease of use. The scales also exhibited high convergent, discriminant, and factorial validity. In both studies, usefulness had a greater correlation with usage behavior than did ease of use, though both were significantly correlated with current usage and future usage. Regression analyses suggest that perceived ease of use may actually be a casual antecedent to perceived usefulness, as opposed to a direct determinant of system usage.
Every Monday morning, Pathe´ Theaters in the Netherlands decides which movies in its cinemas to retain and which to replace. It must choose replacement movies from those available at that time. We implemented the SilverScreener model, a mathematical-programming system [Swami, Eliashberg, and Weinberg 1999] to help Pathe´ managers make those decisions for one six-screen theater and tested its performance against the performance of two unaided similar multiscreen cinemas. Using Pathe´'s historical data, managerial judgment, and theater-specific factors, we developed an attendance-forecasting system. While a fully controlled experiment was not possible, the revenues at the theater using the SilverScreener recommendations were higher than those at the two comparable theaters. Managerial attitudes towards the modeling system improved after implementation of SilverScreener.
A wide variety of specific Decision Support Systems have been and can be built using Internet and Web technologies. This survey article is a focused and updated version of Power (2002) Chapter 11 "Building Web-based and Interorganizational Decision Support Systems". The survey emphasizes the what, how and why of building Web-based DSS. Also, Web-based examples of all five major categories of DSS, communications-driven, data-driven, document-driven, knowledge-driven and model-driven, are summarized and analyzed.
There are an increasing number of litigants who are forced to represent themselves in court. This causes havoc in the judicial system and raises issues of access to justice. We believe that important support for unrepresented litigants can be provided by the construction of web-based legal decision support systems. We discuss tools we have constructed for building web-based legal decision support systems and give examples from the domains of Family Law and eligibility for legal aid. We also illustrate how such decision support tools can help litigants negotiate their disputes.
To improve forecasting accuracy, combine forecasts derived from methods that differ substantially and draw from different sources of information. When feasible, use five or more methods. Use formal procedures to combine forecasts: An equal-weights rule offers a reasonable starting point, and a trimmed mean is desirable if you combine forecasts resulting from five or more methods. Use different weights if you have good domain knowledge or information on which method should be most accurate. Combining forecasts is especially useful when you are uncertain about the situation, uncertain about which method is most accurate, and when you want to avoid large errors. Compared with errors of the typical individual forecast, combining reduces errors. In 30 empirical comparisons, the reduction in ex ante errors for equally weighted combined forecasts averaged about 12.5% and ranged from 3 to 24 percent. Under ideal conditions, combined forecasts were sometimes more accurate than their most accurate components.
In spite of the high financial stakes involved in marketing new motion pictures, marketing science models have not been applied to the prerelease market evaluation of motion pictures. The motion picture industry poses some unique challenges. For example, the consumer adoption process for movies is very sensitive to word-of-mouth interactions, which are difficult to measure and predict before the movie has been released. In this article, we undertake the challenge to develop and implement MOVIEMOD—a prerelease market evaluation model for the motion picture industry. MOVIEMOD is designed to generate box-office forecasts and to support marketing decisions for a new movie after the movie has been produced (or when it is available in a rough cut) but before it has been released. Unlike other forecasting models for motion pictures, the calibration of MOVIEMOD does not require any actual sales data. Also, the data collection time for a product with a limited lifetime such as a movie should not take too long. For MOVIEMOD it takes only three hours in a “consumer clinic” to collect the data needed for the prediction of box-office sales and the evaluation of alternative marketing plans.
The model is based on a behavioral representation of the consumer adoption process for movies as a macroflow process. The heart of MOVIEMOD is an interactive Markov chain model describing the macro-flow process. According to this model, at any point in time with respect to the movie under study, a consumer can be found in one of the following behavioral states: undecided, considerer, rejecter, positive spreader, negative spreader, and inactive. The progression of consumers through the behavioral states depends on a set of movie-specific factors that are related to the marketing mix, as well as on a set of more general behavioral factors that characterize the movie-going behavior in the population of interest. This interactive Markov chain model allows us to account for word-of-mouth interactions among potential adopters and several types of word-of-mouth spreaders in the population. Marketing variables that influence the transitions among the states are movie theme acceptability, promotion strategy, distribution strategy, and the movie experience. The model is calibrated in a consumer clinic experiment. Respondents fill out a questionnaire with general items related to their movie-going and movie communication behavior, they are exposed to different sets of information stimuli, they are actually shown the movie, and finally, they fill outpostmovie evaluations, including word-of-mouth intentions.These measures are used to estimate the word-of-mouth parameters and other behavioral factors, as well as the movie-specific parameters of the model.
MOVIEMOD produces forecasts of the awareness, adoption intention, and cumulative penetration for a new movie within the population of interest for a given base marketing plan. It also provides diagnostic information on the likely impact of alternative marketing plans on the commercial performance of a new movie. We describe two applications of MOVIEMOD: One is a pilot study conducted without studio cooperation in the United States, and the other is a full-fledged implementation conducted with cooperation of the movie's distributor and exhibitor in the Netherlands. The implementations suggest that MOVIEMOD produces reasonably accurate forecasts of box-office performance. More importantly, the model offers the opportunity to simulate the effects of alternative marketing plans. In the Dutch application, the effects of extra advertising, extra magazine articles, extra TV commercials, and higher trailer intensity (compared to the base marketing plan of the distributor) were analyzed. We demonstrate the value of these decision-support capabilities of MOVIEMOD in assisting managers to identify a final plan that resulted in an almost 50% increase in the test movie's revenue performance, compared to the marketing plan initially contemplated. Management implemented this recommended plan, which resulted in box-office sales that were within 5% of the MOVIEMOD prediction. MOVIEMOD was also tested against several benchmark models, and its prediction was better in all cases.
An evaluation of MOVIEMOD jointly by the Dutch exhibitor and the distributor showed that both parties were positive about and appreciated its performance as a decision-support tool. In particular, the distributor, who has more stakes in the domestic performance of its movies, showed a great interest in using MOVIEMOD for subsequent evaluations of new movies prior to their release. Based on such evaluations and the initial validation results, MOVIEMOD can fruitfully (and inexpensively) be used to provide researchers and managers with a deeper understanding of the factors that drive audience response to new motion pictures, and it can be instrumental in developing other decision-support systems that can improve the odds of commercial success of new experiential products.
The primary objective of this paper is to develop a parsimonious model for forecasting the gross box-office revenues of new motion pictures based on early box office data. The paper also seeks to provide insights into the impact of distribution policies on the adoption of new products. The model is intended to assist motion picture exhibitor chains (retailers) in managing their exhibition capacity and in negotiating exhibition license agreements with distributors (studios), by allowing them to project the box-office potential of the movies they plan to or currently exhibit based on early box-office results. It is also of interest to practitioners in other software industries (e.g., music, books, CD-ROMs) where the distribution intensity is highly variable over the product life cycle and is an important determinant of new product adoption patterns. The model and its extensions are of interest to academic researchers interested in modeling distribution effects in new product adoption, as well as forecasters looking for ways to leverage historical data on related products to forecast the sales of new products.
We draw upon a queuing theory framework to conceptualize stochastically the consumer's movie adoption process in two steps—the time to decide to see the new movie, and the time to act on the adoption decision. The parameter for the time-to-decide process captures the intensity of information intensity flowing from various information sources, while the parameter for the time-to-act process is related to the delay created by limited distribution intensity and other factors. Our conceptualization extends existing new product forecasting models, which assume that consumers act instantaneously on the motivating information they receive about the new product. The resulting model is parsimonious, yet it accommodates a wide range of adoption patterns. In addition, the stochastic formulation allows us to quantify the uncertainty surrounding the expected adoption pattern. In the empirical testing, we focus on the most parsimonious version of the modeling framework. BOXMOD-I, a model that assumes stationarity with respect to the two shape parameters that characterize the adoption process. The model produces fairly accurate early forecasts using at most the first three weeks of data for calibration, and the predictive performance of the model compares favorably with benchmark models. We propose extensions of the basic model that account for more realistic non-stationary distribution intensity patterns—including a “wide release” pattern that relies on intensive distribution and promotion, and a “platform release” pattern that involves a gradual buildup of distribution intensity. Finally, we present an adaptive weighing scheme that combines initial parameter estimates obtained from a meta-analysis procedure with estimates obtained from early data to produce forecasts of box-office revenues for a new movie when little or no box-office data are available.
An important finding from the empirical testing is that motion picture box-office revenue patterns display remarkable empirical regularity. We find that there are only three classes of adoption patterns, and these can all be represented within the basic model by using a two-parameter. Exponential or Erlang-2 probability distribution, or a three parameter Generalized Gamma distribution. We also find that cumulative box-office revenues can be predicted with reasonable accuracy (often within 10% of the actual) using as little as two or three data points. However, our attempts to predict revenue patterns without any sales data meet with limited success. While the scale parameter can be estimated reasonably well from a historical database of parameter values, we find that it is considerably more difficult to predict the shape parameters using historical data.
The parsimony we seek in developing the model comes at the cost of several limiting assumptions. We assume that the time-to-decide subprocess and the time-to-act subprocess are independent, which may not be the case if decisions on continued exhibition by retailers are endogenously related to box-office revenues over the life cycle. In the basic model formulation, we also assume that the time-to-act process can be represented by an exponential distribution, which may not always be the case. While we provide some empirical evidence to support these assumptions, further research could relax these and other assumptions to enrich the basic model, although this would entail some loss in parsimony.
Since the early 1970s, decision support systems (DSS) technology and applications have evolved significantly. Many technological and organizational developments have exerted an impact on this evolution. DSS once utilized more limited database, modeling, and user interface functionality, but technological innovations have enabled far more powerful DSS functionality. DSS once supported individual decision-makers, but later DSS technologies were applied to workgroups or teams, especially virtual teams. The advent of the Web has enabled inter-organizational decision support systems, and has given rise to numerous new applications of existing technology as well as many new decision support technologies themselves. It seems likely that mobile tools, mobile e-services, and wireless Internet protocols will mark the next major set of developments in DSS. This paper discusses the evolution of DSS technologies and issues related to DSS definition, application, and impact. It then presents four powerful decision support tools, including data warehouses, OLAP, data mining, and Web-based DSS. Issues in the field of collaborative support systems and virtual teams are presented. This paper also describes the state of the art of optimization-based decision support and active decision support for the next millennium. Finally, some implications for the future of the field are discussed.
Discrete values have important roles in data mining and knowledge discovery. They are about intervals of numbers which are more concise to represent and specify, easier to use and comprehend as they are closer to a knowledge-level representation than continuous values. Many studies show induction tasks can benefit from discretization: rules with discrete values are normally shorter and more understandable and discretization can lead to improved predictive accuracy. Furthermore, many induction algorithms found in the literature require discrete features. All these prompt researchers and practitioners to discretize continuous features before or during a machine learning or data mining task. There are numerous discretization methods available in the literature. It is time for us to examine these seemingly different methods for discretization and find out how different they really are, what are the key components of a discretization process, how we can improve the current level of research for new development as well as the use of existing methods. This paper aims at a systematic study of discretization methods with their history of development, effect on classification, and trade-off between speed and accuracy. Contributions of this paper are an abstract description summarizing existing discretization methods, a hierarchical framework to categorize the existing methods and pave the way for further development, concise discussions of representative discretization methods, extensive experiments and their analysis, and some guidelines as to how to choose a discretization method under various circumstances. We also identify some issues yet to solve and future research for discretization.
In 1992, DeLone and McLean suggested that the dependent variable for information systems (IS) research is IS Success. Their research resulted in the widely cited DeLone and McLean (D&M) IS Success Model, in which System Quality, Information Quality, Use, User Satisfaction, Individual Impact, and Organizational Impact are distinct, but related dimensions of IS success. Since the original IS Success Model was published, research has developed a better understanding of IS success. Meanwhile, comprehensive and integrative research on the variables that influence IS success has been lacking. Therefore, we examine the literature on the independent variables that affect IS success. After examining over 600 articles, we focused our attention on integrating the findings of over 140 studies. In this research, we identify 43 specific variables posited to influence the different dimensions of IS success, and we organize these success factors into five categories based on the Leavitt Diamond of Organizational Change: task characteristics, user characteristics, social characteristics, project characteristics, and organizational characteristics. Next, we identify 15 success factors that have consistently been found to influence IS success: Enjoyment, Trust, User Expectations, Extrinsic Motivation, IT Infrastructure, Task Compatibility, Task Difficulty, Attitudes Toward Technology, Organizational Role, User Involvement, Relationship with Developers, Domain Expert Knowledge, Management Support, Management Processes, and Organizational Competence. Finally, we highlight gaps in our knowledge of success factors and propose a road map for future research.
Valid measurement scales for predicting user acceptance of computers are in short supply. Most subjective measures used in practice are unvalidated, and their relationship to system usage is unknown. The present research develops and validates new scales for two specific variables, perceived usefulness and perceived ease of use, which are hypothesized to be fundamental determinants of user acceptance. Definitions for these two variables were used to develop scale items that were pretested for content validity and then tested for reliability and construct validity in two studies involving a total of 152 users and four application programs. The measures were refined and streamlined, resulting in two six-item scales with reliabilities of .98 for usefulness and .94 for ease of use. The scales exhibited high convergent, discriminant, and factorial validity. Perceived usefulness was significantly correlated with both self-reported current usage (r=.63, Study 1) and self-predicted future usage (r =.85, Study 2). Perceived ease of use was also significantly correlated with current usage (r=.45, Study 1) and future usage (r=.59, Study 2). In both studies, usefulness had a significantly greater correlation with usage behavior than did ease of use. Regression analyses suggest that perceived ease of use may actually be a causal antecedent to perceived usefulness, as opposed to a parallel, direct determinant of system usage. Implications are drawn for future research on user acceptance.
This article presents two alternative explanations for the role of stars in motion pictures. Either informed insiders signal project quality by hiring an expensive star, or stars capture their expected economic rent. These approaches are tested on a sample of movies produced in the 1990s. Means comparisons suggest that star-studded films bring in higher revenues. However, regressions show that any big budget investment increases revenues. Sequels, highly visible films and "family oriented" ratings also contribute to revenues. A higher return on investment is correlated only with G or PG ratings and marginally with sequels. This is consistent with the "rent capture" hypothesis. Copyright 1999 by University of Chicago Press.
For MIS specialists and nonspecialists alike, teacher and consultant Dan Power provides a readable, comprehensive, understandable guide to the concepts and applications of decision support systems. Power defines DSS broadly: interactive computer-based systems and subsystems that help people use computer communications, data, documents, knowledge, and models to solve problems and make decisions. This book covers an expanded framework for categorizing Decision Support Systems (DSS), a general managerial and technical perspective on building DSS, details and examples of the general types of DSS, and tools and issues associated with assessing proposals for DSS projects. A glossary and DSS readiness audit questions give special, ongoing value to all readers. Free eBook at https://scholarworks.uni.edu/facbook/67/
This contribution deals with the Austrian research project AURORA and the application of high performance computing (HPC) in the field of microelectronics. In the first part the ‘Spezialforschungsbereich’ AURORA - Advanced Models, Applications, and Software Systems for High Performance Computing - is presented which is funded by the Austrian ‘Fonds zur Forderung der wissenschaftlichen Forschung’. Seven research groups belonging to different institutes of the ‘Universitat Wien’ and the ‘Technische Universitat Wien’ are participating in AURORA, thus covering the fields computer science, statistics and operations research, numerical mathematics, electrochemistry, and microelectronics. The second part deals with the activities concerning the application of HPC to the simulation of the behaviour of microelectronic devices and their technological process steps in order to intensify the research capabilities of the simulation tools.
A new software tool, business intelligence tools for plant floor decision support is introduced by the major vendors for manufacturing execution system (MES), supervisory control and data acquisition (SCADA), and human machine interface (HMI) applications. Microsoft's Window Distributed Internet Applications for Manufacturing (DNA-M) architecture is used in many plant operations. Component object model (COM) integration, Visual Basic for applications (VBA) and extensible markup language (XML) are used to develop decision support tools. Object linking and embedding (OLE) is used for process controls. This helps plant management to make critical business decisions. Real time data analysis allows company to be more responsive.
A new model approach is developed to evaluate the market performance of new film releases as a function of advertising. The proposed model sequentially links planned advertising expenditures for a new film introduction to awareness, intention to see the film, as well as projected ticket sales at the box office. This paper illustrates how the model may be used by a movie studio to evaluate alternative film introduction strategies based on proposed allocations of advertising expenditures as well as theater distribution intensities over a film's life cycle.
We give conditions ensuring that multilayer feedforward networks with as few as a single hidden layer and an appropriately smooth hidden layer activation function are capable of arbitrarily accurate approximation to an arbitrary function and its derivatives. In fact, these networks can approximate functions that are not differentiable in the classical sense, but possess only a generalized derivative, as is the case for certain piecewise differentiable functions. The conditions imposed on the hidden layer activation function are relatively mild; the conditions imposed on the domain of the function to be approximated have practical implications. Our approximation results provide a previously missing theoretical justification for the use of multilayer feedforward networks in applications requiring simultaneous approximation of a function and its derivatives.
We developed STEP-UP, a database-intensive, decision-support system for dislocated workers. We modeled the work positions at a micro- and macro-level and created tailored profiles for individuals to reflect prior positions, training, certifications, and interests. With the profile, career counselors matched employees to labor-market positions or identified training programs in growth industries. Also, giving the prospective employers an indication of the wealth of skilled employees, STEP-UP could provide client matches for job openings. We have continued to extend the capabilities of STEP-UP and offer it as a Web-based system. We expect that more decision support systems like STEP-UP will be developed for use in human resource decision-making situations.
This study explores the factors related to success in the motion picture industry and found that familiarity with actors, characters, and story, as well as kudos from reviewers and industry association, are key factors. The authors argue that increasing control by the marketing side of the industry is leading to sequelization, imitation, and higher demand for popular stars in response to the rise in the number of competitors and new exhibition technologies.
A current commercial web-based Judicial Decision Support System (JDSS) in the area of criminal law is in use in New York State. It assists hundreds of judges statewide in questions of sentencing, lesser included offenses, plea bargaining and statutory interpretation. Maintenance of this system's rule base with respect to sentencing has revealed instances where interactions between statutes imply conflicting rules. Resolution of such conflicts requires a varied set of strategies; occasionally no satisfactory resolution is possible. Most such problems have been found to arise not from open textured terms deliberately employed, but from avoidable deficiencies in drafting. Rather than view these anomalies as limitations on the rule-based approach, one may view them as an opportunity to promote a resolution by consensus preferable to the traditional common law approach of scattered lower court decisions ultimately clarified by authoritative appellate ruling. The current call for re-codification of the New York penal laws presents an opportunity to employ such systems in a systematic way when drafting legislation.
I examined the performance of motion pictures released in the United States and Canada between October 1987 and October 1989. Performance was measured by two dependent variables: domestic rentals (RENTs) and the length of run (LOR) of each film. In addition, a new independent variable designed to measure the impact of competition on motion picture performance was hypothesized. LOR was found to be a reliable proxy for RENTs in predicting performance and will allow researchers to expand the base of films that can be included in future studies. Further, the independent variable for competition was found to have a significant negative relation with RENTs as a predictor of performance. That is, as the concentration ratio for a specific film increases, the competition that film faces increases; as a result, the RENTs for that specific film decrease.
The Internet technology has evolved very rapidly over the past few years. Due to its multimedia capability, the World Ž . Wide Web WWW or Web is the most popular and visible component of the Internet. It is being increasingly used to support various activities of the product development process. This paper is concerned with providing design for Ž . manufacture and assembly DFMA techniques on the Internet. An experiment is conducted to show how a well-known Ž . design for assembly DFA technique can be converted into a web-based version which is functionally equivalent to its version on a standalone workstation. Four important insights have been gained from the experiment. The web-based client and server architecture is found to be attractive for collaborative DFMA. The client-side web scripting can be exploited to Ž . develop generic frameworks for developing and applying different design for X DFX techniques, more importantly, in an integrated way. In addition, web-based DFX techniques provide more opportunities for integration with other decision-sup-Ž . Ž . port systems such as Computer Aided Design CAD , Computer Aided Process Planning CAPP and Computer Aided Ž . Production Management CAPM in the product realisation process. However, issues such as interactivity and security remain to be addressed. q 1999 Elsevier Science B.V. All rights reserved.
This paper attempts to shed light on the following research questions: When a firm introduces a new product (or service) how can it effectively use the different information sources available to generate reliable new product performance forecasts? How can the firm account for varying information availability at different stages of the new product launch and generate forecasts at each stage? We address these questions in the context of the sequential launches of motion pictures in international markets.
Players in the motion picture industry require forecasts at different stages of the movie launch process to aid decision-making, and the information sets available to generate such forecasts vary at different stages. Despite the importance of such forecasts, the industry struggles to understand and predict sales of new movies in domestic and overseas markets.
We develop a Bayesian modeling framework that predicts first-week viewership for new movies in both domestic and several international markets. We focus on the first week because industry players involved in international markets (studios, distributors, and exhibitors) are most interested in these predictions. We draw on existing literature on forecasting performance of new movies to formulate our model. Specifically, we model the number of viewers of a movie in a given week using a Poisson count data model. The number of screens, distribution strategy, movie attributes such as genre, and presence/absence of stars are among the factors modeled to influence viewership. We employ a hierarchical Bayes formulation of the Poisson model that allows the determinants of viewership to vary across countries. We adopt the Bayesian approach for two reasons: First, it provides a convenient framework to model varying assumptions of information availability; specifically, it allows us to make forecasts by combining different sources of information such as domestic and international market-specific data. Second, this methodology provides us with the entire distribution of the new movie's performance forecast. Such a predictive distribution is more informative than a point estimate and provides a measure of the uncertainty in the forecasts.
We propose a Bayesian prediction procedure that provides viewership forecasts at different stages of the new movie release process. The methodology provides forecasts under a number of information availability scenarios. Thus, forecasts can be obtained with just information from a historical database containing data on previous new product launches in several international markets. As more information becomes available, the forecasting methodology allows us to combine historical information with data on the performance of the new product in the domestic market and thereby to make forecasts with less uncertainty and greater accuracy.
Our results indicate that for all the countries in the data set the number of screens on which a movie is released is the most important influence on viewership. Furthermore, we find that local distribution improves movie sales internationally in contrast to the domestic market. We also find evidence of similar genre preferences in geographically disparate countries. We find that the proposed model provides accurate forecasts at the movie-country level. Further, the model outperforms all the extant models in the marketing literature that could potentially be used for making these forecasts. A comparison of root mean square and mean absolute errors for movies in a hold out sample shows that the model that combines information available from the different sources generates the lowest errors. A Bayesian predictive model selection criterion corroborates the superior performance of this model. We demonstrate that the Bayesian model can be combined with industry rules of thumb to generate cumulative box office forecasts.
In summary, this research demonstrates a Bayesian modeling framework that allows the use of different information sources to make new product forecasts in domestic and international markets. Our results underscore the theme that each movie is unique as is each country—and viewership results from an interaction of the product and the market. Hence, the motion picture industry should use both product-specific and market-specific information to make new movie performance forecasts.
The expected error variance of a combined forecast is necessarily lower than that of an individual forecast, but in practice there may be considerable variation around these expected values. This paper introduces a measure of the benefit from combining, the probability of a reduction in error variance, which recognizes this problem. The measure is applied to data on the forecasts and forecasting methods of a panel of U.S. economists to determine how the benefits of combining vary with the number of forecasts combined, and with the diversity in theories and techniques among the component forecasts.
Supply chain issues have been given much attention. Various technologies and concepts have been applied to improving and optimizing supply chain performance. However, few methods to explore supply chain inter-relationships, detect process key problems and co-ordinate planning processes in different supply chain partners are available. A Web-based co-ordinated planning process supported by quality function deployment (QFD) approach is proposed in this research. The planning method is focused on integrating planning processes in supply chains by optimizing each planning process and interactively adjusting key parameters in different business processes. The QFD approach is employed to inter-relate different business processes and detect key problems through Internet technique application, so that the global solution can be heuristically improved. The planning method imitates the real-world supply chain planning environment and provides a mechanism for decision-makers to communicate with quantitative information in planning processes through the Web system. An illustrative case study in packaging industry is conducted to describe the planning procedure. The result of the example shows prospect of the method in improving supply chain cooperation. The approach is expected to facilitate supply chain planning and support managers to solve targeted problems more efficiently.
The technology for building knowledge-based systems by inductive inference from examples has been demonstrated successfully in several practical applications. This paper summarizes an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail. Results from recent studies show ways in which the methodology can be modified to deal with information that is noisy and/or incomplete. A reported shortcoming of the basic algorithm is discussed and two means of overcoming it are compared. The paper concludes with illustrations of current research directions.
Customer Relationship Management (CRM) is a valuable concept for hospitals to establish long-term physician relationships. Given predetermined reimbursement amounts, clinical interventions by physicians can significantly impact hospital profitability and quality. Therefore, disseminating quality and cost information to physicians can build lasting relationships, while insuring financial stability.This paper presents a CRM approach adopted by a hospital through a web-based Physician Profiling System (PPS). We discuss physician involvement in PPS development and present a high-level cost-benefit analysis. Post-deployment results indicate that PPS strengthened relationship with physicians, improved efficiency of clinical operations, while simultaneously improving patient satisfaction.
Companies have rushed to set up presences on the World Wide Web. In most instances, they are advertising their products and services, and in some instances, are actually delivering them over the Internet. Many of these companies are small, and there is at least anecdotal evidence that small companies are at the forefront of commercial use of the Web. In this paper, we consider various perspectives for assessing the role and use of the Web. We argue that most small companies will view the Web as an electronic marketplace. We consider the attraction of the Web as a marketplace for small companies, and the key strategic drivers that are moving small companies to join the Web. We also suggest a number of inhibitors that will make the Web less attractive for small companies in the future. The result is a model that can be used to understand the position of small companies with respect to the Web. Despite the youth of this new medium, some marketing paradigms common to many entrants are emerging. We discuss these paradigms and give examples of their use. We briefly review some successful cases.
In this paper, we provide an integrated framework for portfolio selection, which is adaptable to the needs of financial organizations and individual investors, and as an organized approach of selecting efficient portfolios for investments. We focus our discussion on the implementation of this framework for a Web-based Decision Support System (DSS) based on our prototype named WPSS—A Web-based Portfolio Selection System for Chinese financial markets. In this system, we adopt technologies such as online analytical processing as an add-on tool for analytical purpose, as well as using Parallel Virtual Machine (PVM) to improve overall performance.
Despite the gainful use of the Web as a communication medium, recent research suggests that very little work has been done to leverage this new technology for enabling changes in the planning process. This paper, motivated by a situation at a Fortune 100 company, describes a prototype Web-based decision support system (DSS) for the management of service contracts, which are being increasingly purchased by a variety of businesses. The planning for spare parts needed to support service contracts is hampered by unpredictable and extremely low demands, thereby necessitating a subjective manual approach that is inherently non-standardized and non-coordinated among the various constituents of the organization. In this paper, we describe how a Web-based system can enable the standardization of the process of managing and supporting service contracts. In addition, our DSS supports geographically and functionally dispersed decision-making roles, thereby displaying characteristics of an organizational decision support system (ODSS).
The SenseViewer Knowledge Management System (KMS) helps users retrieve and understand information fragments and their attributes by linking them to underlying arguments within their topic realm and exposing their context within source documents. This paper examines SenseViewer, its relationship to rapid knowledge construction, and its use to support the drafting and passage of a new Criminal Procedural Codex by the Russian DUMA. It considers what set of KM functions and tools facilitate the legislative process and dissemination of knowledge to the populace. SenseViewer illustrates a new generation of web-based e-government KMS.
Enterprises which are distributed in space and/or which are composed as a temporary joint venture of legally different units recently often called virtual (extended) enterprises. Planning, design and operation (management) goals and requirements of such firms are generally different from those of single, centralized enterprises. The basic feature of an extended (virtual) enterprise is that the co-operating units of it keep their independence during the life-cycle of the co-operation—what is well regulated by the rules of the given conglomerate. It has to be accepted—on the other hand—that several basic functionalities and goals are the same for all types of distributed, large, complex organizations, which are the targets of our recent study.
The articles published by the Annals of Eugenics (1925–1954) have been made available online as an historical archive intended for scholarly use. The work of eugenicists was often pervaded by prejudice against racial, ethnic and disabled groups. The online publication of this material for scholarly research purposes is not an endorsement of those views nor a promotion of eugenics in any way.