Figure - available from: Applied Artificial Intelligence
This content is subject to copyright. Terms and conditions apply.
Source publication
The stock market is viewed as an unpredictable, volatile, and competitive market. The prediction of stock prices has been a challenging task for many years. In fact, many analysts are highly interested in the research area of stock price prediction. Various forecasting methods can be categorized into linear and non-linear algorithms. In this paper,...
Citations
... A study by Zhang et al. (2019) suggested an innovative generative adversarial network (GAN) architecture employing a multi-layer perceptron (MLP) as a discriminator and LSTM as a generator for predicting stock closing prices. Fathali, Kodia, and BenSaid (2022) used deep learning networks to predict stock prices on the Indian National Stock Exchange. RNN, LSTM, and CNN have been used to analyze NIFTY 50 stock prices. ...
The intricate and unpredictable nature of stock markets underscores the importance of precise forecasting for timely detection of downturns and subsequent rebounds. Various factors, including news, rumors surrounding events or companies, market sentiments, and governmental policies, can significantly impact stock prices. Nevertheless, the precision of current methods remained insufficient until the adoption of artificial neural network architectures like long short-term memory (LSTM). The aim of this study is to create a precise AI-driven platform tailored for both the Indian and international stock markets. This platform is designed to assist retail investors in navigating digital environments by employing various LSTM algorithms. Its primary goals include predicting stock price fluctuations, pinpointing potential investment prospects, and refining trading strategies. The application aims to leverage advanced LSTM algorithms to analyze historical market data, recognize patterns, and provide real-time insights. It will take past price and process it through LSTM algorithms to take a logical decision. In the quest to broaden retail participation in the capital markets, the effort is to develop an application for novice investors who either have no time in research or are the victims of financial mis-selling and enable them to leverage the technology to their advantage.
... Using the MSE metric, the models' performance was measured. When compared to RNN and CNN models, these errors are observed to be smaller in the LSTM model (Fathali, Zahra and Ben Said, 2022). ...
This paper aims to study stock prediction techniques, particularly the ones involved with neural network methods. It focuses on three sub-parts. Firstly, the focus is on the neural network application for forecasting stock market values due to its capacity to detect patterns in nonlinear and chaotic systems. Then, artificial intelligence algorithm is compared with traditional and current techniques being used for forecasting stock market trend. Thirdly, the effectiveness of the algorithm is checked on several Indian and US listed stocks, and compare their prediction parameters and factors affecting Indian stock market.
... This approach not only facilitates the identification of general market trends but also contributes to the refinement of prediction models for increased reliability. Fathali, Kodia, and Said (2022) provide a comparative analysis of different deep learning networks, including RNN, LSTM, and Convolutional Neural Networks (CNN), for predicting the NIFTY 50 stock prices. Their research illustrates the critical role of feature selection and hyperparameter optimization in improving the quality of predictions, thereby addressing some of the inherent challenges in stock market forecasting. ...
... However, the effectiveness of these models is contingent upon their ability to navigate the complexities of financial datasets and the dynamic nature of the stock market. Fathali, Kodia, and Said (2022) address the challenges in stock market prediction by focusing on the Indian National Stock Exchange, employing deep learning networks for time series analysis and prediction. Their comparative analysis reveals the critical role of feature selection and hyperparameter optimization in enhancing the prediction quality. ...
In the rapidly evolving landscape of financial markets, the quest for accurate stock market predictions has never been more critical. This paper delves into the transformative potential of neural network models in forecasting stock market movements, offering a comprehensive examination of their effectiveness compared to traditional predictive models. With a focus on the evolution of stock market prediction methodologies, this study aims to uncover the nuanced dynamics of neural networks, their comparative analysis with other models, and the pivotal role of data preprocessing in enhancing prediction accuracy. Employing a qualitative analysis framework, the research meticulously synthesizes findings from selected studies, highlighting the superior OPEN ACCESS performance of neural network models in capturing complex market patterns and adapting to volatility. The results underscore the significant impact of data quality and quantity, architectural nuances of neural networks, and the strategic implications for investors navigating the stock market's unpredictability. Despite the promising outcomes, the study acknowledges inherent challenges in the real-world application of these models, including data imperfections and the complexity of financial ecosystems. Conclusively, the paper advocates for ongoing innovation, interdisciplinary collaboration, and the strategic integration of advanced neural network architectures to overcome existing limitations. Recommendations emphasize the critical need for high-quality, diverse datasets and continuous model refinement to harness the full predictive power of neural networks in stock market forecasting. This study not only illuminates the path forward for investors and financial analysts but also sets the stage for future research in this dynamic field. INTRODUCTION Background of the Study The Evolution of Stock Market Prediction Models The quest for accurate stock market predictions has been a focal point of financial research for decades. The evolution of prediction models has transitioned from basic statistical methods to sophisticated machine learning techniques, reflecting the advancements in computational power and data analysis methodologies. Kolte et al. (2022) emphasize the unpredictable and volatile nature of the stock market, which complicates the task of forecasting stock prices. Despite these challenges, the integration of machine learning, particularly deep learning models like Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks, has shown promising results in enhancing prediction accuracy. The application of neural networks in stock market prediction represents a significant shift towards data-driven, automated analysis. Paliwal and Sharma (2022) highlight the use of evolution algorithms to optimize neural network architectures and hyperparameters, underscoring the complexity and the need for precision in model selection to achieve better prediction outcomes. This approach not only facilitates the identification of general market trends but also contributes to the refinement of prediction models for increased reliability. Fathali, Kodia, and Said (2022) provide a comparative analysis of different deep learning networks, including RNN, LSTM, and Convolutional Neural Networks (CNN), for predicting the NIFTY 50 stock prices. Their research illustrates the critical role of feature selection and hyper-parameter optimization in improving the quality of predictions, thereby addressing some of the inherent challenges in stock market forecasting. Menon, Singh, and Parekh (2019) review various neural network models for stock market prediction, acknowledging the recent advancements in machine learning and neural networks. Their work sheds light on the diverse methodologies employed to decipher the complex patterns of the stock market, indicating a trend towards more adaptive and sophisticated predictive models.
... A DL model can effectively outperform traditional SPF systems in terms of accuracy. CNNs 50-54 and recurrent neural network (RNN) such as LSTM or gated recurrent unit (GRU), [55][56][57][58][59][60] and BiLSTM 61-64 are extensively employed for SPF systems. Table 3 presents a summary of DL-based approaches for SPF. ...
We introduce a comprehensive analysis of several approaches used in stock price forecasting, including statistical, machine learning, and deep learning models. The advantages and limitations of these models are discussed to provide an insight into stock price forecasting. Traditional statistical methods, such as the autoregressive integrated moving average and its variants, are recognized for their efficiency, but they also have some limitations in addressing non-linear problems and providing long-term forecasts. Machine learning approaches, including algorithms such as artificial neural networks and random forests, are praised for their ability to grasp non-linear information without depending on stochastic data or economic theory. Moreover, deep learning approaches, such as convolutional neural networks and recurrent neural networks, can deal with complex patterns in stock prices. Additionally, this study further investigates hybrid models, combining various approaches to explore their strengths and counterbalance individual weaknesses, thereby enhancing predictive accuracy. By presenting a detailed review of various studies and methods, this study illuminates the direction of stock price forecasting and highlights potential approaches for further studies refining the stock price forecasting models.
... There has been no consensus on how the LSTM-only model would compare with the CNN-only model, as the prediction performance has varied in different scenarios. Some researchers compared standalone models and concluded that CNN-only performed better than LSTM-only, Stacked-LSTM, Bidirectional-LSTM (BiLSTM) [28,71] and GRU [68] for daily stock price prediction (regression); while on the contrary, Kamalov [81] claimed that LSTM-only outperformed CNN-only, MLP, and SVR using 10 years of daily stock price data of four US companies, for a classification type of prediction; and Fathali et al. [82] reported that LSTM-only outperformed CNN-only and RNN for a regression problem on NIFTY 50 stock prices. ...
Financial time series prediction, whether for classification or regression, has been a heated research topic over the last decade. While traditional machine learning algorithms have experienced mediocre results, deep learning has largely contributed to the elevation of the prediction performance. Currently, the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking, making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better, what techniques and components are involved, and how the model can be designed and implemented. This review article provides an overview of techniques, components and frameworks for financial time series prediction, with an emphasis on state-of-the-art deep learning models in the literature from 2015 to 2023, including standalone models like convolutional neural networks (CNN) that are capable of extracting spatial dependencies within data, and long short-term memory (LSTM) that is designed for handling temporal dependencies; and hybrid models integrating CNN, LSTM, attention mechanism (AM) and other techniques. For illustration and comparison purposes, models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input, output, feature extraction, prediction, and related processes. Among the state-of-the-art models, hybrid models like CNN-LSTM and CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model. Some remaining challenges have been discussed, including non-friendliness for finance domain experts, delayed prediction, domain knowledge negligence, lack of standards, and inability of real-time and high-frequency predictions. The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review, compare and summarize technologies and recent advances in this area, to facilitate smooth and informed implementation, and to highlight future research directions.
... Similarly, Kumar and Thenmozhi [15] applied various techniques to predict the Nifty index; however, this study dates back to an earlier period. More recently, Fathali, Kodia, and Ben Said [16] employed different neural network models to forecast the Nifty index. In contrast, our study takes a unique approach by conducting a comparative analysis of random walk (RW), autoregressive moving average (ARIMA) and artificial neural network (ANN) forecasting models, providing valuable insights into their respective performances. ...
... In particular, the oil and gas sector [13], known for its complex market dynamics and susceptibility to various external factors, heavily relies on accurate predictions to drive effective decision-making and risk management strategies. The emergence of advanced technologies and machine learning techniques has revolutionized stock market prediction [14][15][16][17][18][19][20], enabling more sophisticated and accurate forecasting models. Deep learning models, such as Recurrent Neural Networks [21], Convolutional Neural Networks [22,23] and Long Short-Term Memory (LSTM) [24][25][26][27][28][29][30] networks, have shown great promise in capturing complex patterns and dependencies in time series data, making them well-suited for predicting stock prices. ...
... The prediction is guided by analyzing the trend based on the historical of the last few years [3]. Generally, in order to predict the stock price of a company, three major analysis prediction methods have been suggested, (1) fundamental analysis, (2) technical analysis, and (3) machine learning approach [4], [35]. The fundamental analysis views that economic factors as fundamentals and it is most applicable for long-term predictions. ...
... Different types of ML algorithms [35] are used in the task of prediction. The most common form of ML or DL algorithms is the supervised learning [8]. ...
... Artificial intelligence can analyze large amounts of data and provide predictability. Machine learning and data analytics algorithms can assist in predicting customer behaviors, identifying trends, and optimizing marketing strategies (Fathali et al., 2022). Traditional marketing often involves messages and campaigns targeting general audiences. ...
Purpose- This study aims to provide a bibliometric review of publications where the terms 'digital marketing' and 'artificial intelligence' are used together. Leading publications, authors, countries, and institutions in the Web of Science (WoS) database have been examined to achieve this goal. Additionally, this article investigates the combined use of digital marketing and artificial intelligence. Furthermore, it aims to offer insights into artificial intelligence strategies for marketing that businesses can employ. Methodology- The research employs the technique of bibliometric analysis. The Bibliometrix package within R Studio and its web-based component, Biblioshiny, were utilized for analysis. Searches were conducted in the Web of Science database using the keywords 'Digital Marketing' and 'Artificial Intelligence' in the title, abstract, and keywords sections. Findings- As a result of the analysis, a total of 60 publications authored by 140 researchers and distributed across 46 journals between 2017 and 2023 were identified. Examination of the included publications reveals frequent usage of terms such as 'artificial intelligence,' 'creativity,' 'analytics,' 'impact,' 'expertise,' 'social networks,' 'big data,' 'governance,' 'success,' and 'AI.' Upon scrutinizing the authors' countries, India emerged as the leading contributor, followed by Spain and the USA. Moreover, Finland (370), Spain (92), and France (58) had the highest citation counts. Conclusion- This research aims to contribute to researchers interested in working in digital marketing and artificial intelligence by examining its past and present. For this purpose, 60 relevant studies from the literature were systematically reviewed and analyzed across various categories. Additionally, the examined publications' conceptual, intellectual, and social structures were illuminated. Keywords: Digital marketing, artificial intelligence, AI systems, bibliometric analysis, bibliometrix. JEL Codes: M15, M30, M31
... Artificial intelligence is capable of processing massive amounts of information, identify trends, and predict customer behaviors. This enables the creation of more effective marketing strategies and better outcomes (Fathali et al., 2022). Digital marketing focuses on target audiences and delivers personalized messages. ...
Artificial intelligence (AI) and machine learning technologies are increasingly gaining importance for accurately analyzing consumer behavior and delivering customized advertising content within digital marketing strategies. A rapid increase has been observed in the recent research concerning machine learning and artificial intelligence in the digital marketing literature. This research aims to strategically and thematically present a scientific map of publications using digital marketing, machine learning, and artificial intelligence. For this purpose, the bibliometric analysis method, one of the quantitative research methods, has been used in the study. The data used in this study were obtained from the Scopus database, covering 2007-2023. The gathered data were analyzed and visualized using the Bibliometrix analysis program with its web interface provider, Biblioshiny. A total of 171 publications were reached in the research. There has been an increase in publications since the year 2017. The journal with the most publications is Communications in Computer and Information Science. The most frequently used words are artificial intelligence, marketing, machine learning, commerce, digital marketing, learning systems, machine learning, decision-making, e-learning, and deep learning. Moreover, a co-occurrence network exists between machine learning, marketing, artificial intelligence, digital marketing, and commerce. The highest level of publication collaboration has occurred between the United States of America (USA) and India. The involvement of numerous authors from diverse journals suggests that the topic attracts attention from multiple fields. This study offers an extensive bibliometric analysis to visualize the academic publication landscape of digital marketing, machine learning, and artificial intelligence. Subsequent research is expected to emphasize the real-world applications of these technologies in various industries. The visualization of the data obtained from the analyses in this research holds significance for guiding future studies in this area.
