Figure - available from: Iran Journal of Computer Science
This content is subject to copyright. Terms and conditions apply.
Source publication
Recommendation systems are most commonly used to recommend items for web users. It assists users in the selection of product from millions of product. E-Commerce websites such as AMAZON recommend items to its customers. The recommendation system mainly depends upon the previous history of its users. In this paper, a new User Rating Prediction (URP)...
Similar publications
Collaborative filtering (CF) has proven to be the most prominent and preferable approach in the recommendation systems due to its simplicity and effectiveness. The fundamental philosophy of CF-based recommendation is that similar users have the same rating patterns and similar items obtain similar ratings. However, the accuracy of CF significantly...
This is the era of I-way. The development of high-speed computing and huge storage devices change the working culture of human. It affects the traditional business processes and shifted towards online business. It creates huge problems like overload and irrelevant information which are the causes of confusion both customers as well as enterprise. R...
Researchers and data scientists have developed different Recommender System Algorithms such as Content-Based and Collaborative-Based in order to filter a large amount of information available on the internet and hence, recommend only the relevant and essential content based on the personalized interests of users. Information acquired explicitly by...
Recommendation system is a process of filtering information to retain buyers on e-commerce sites or applications. It is used on all e-commerce sites, social media platform and multimedia platform. This recommendation is based on their own experience or experience between users. In recent days, the graph-based filtering techniques are used for the r...
In the field of Data science and online world, Recommendation Systems (RS) play an important role among the various e-commerce applications. Data sparsity often leads to the problem of precise recommendations in RS as there will be either less number of users or ratings. Collaborative filtering (CF) is one of the key techniques that are used for th...
Citations
... 1. Collaborative filtering (CF) is widely considered to be the most effective way of filtering. This recommendation makes product suggestions to other users in the same domain based on the ratings they have given similar items in the past [6]. It considers the ratings of users who belong to the same category and looks for patterns of similarity in how those users rate items to provide product recommendations to consumers. ...
The recommender system (RS) shows a personalized recommendation by separating the data based on what clients like. Nowadays, people want to buy the most popular products and services to spend the least time shopping. The products are suggested based on what the customer has bought before, what they like, what they say, their profile, the best feature on a website, etc. In this article, we show a hybrid filtering method for book recommendations. That uses the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering technique to meet each person's needs. In addition, reviews of the books are taken into account to figure out the rating. These are grouped into two groups: reviews with ratings and ratings and reviews without reviews and ratings (missing data). In a complete review, the sentiment score is calculated by adding the text from the study that shows how people feel about it. The feeling could be either good or bad. In an incomplete review, the rating is based on the user's demographic information (age, gender, locality & profession). This article also looks at the different types of similarity measures, such as Adjusted Cosine, Pearson Correlation, Euclidean, Manhattan, and Jaccard Similarity. The proposed method is tested on the Amazon book dataset. The RS error is calculated using Root Mean Square Error (RMSE) and Mean Square Error (MSE). The results show that the suggested method has a lower error rate with RMSE (2.63), MSE, and MSE (3.15). This method solves the problems of a cold start and a lack of data while giving them valuable books and amenities. The accuracy of recommendations is measured by precision, recall, and the F-measure.
... Results of the Single Slope scheme displays that a combination of user resemblance and trusted data has significantly enriched the predictive accuracy. However, the presence of fraudster users can affect the accuracy of RS. Kumar et al. (2019) suggested a user rating prediction (URP) scheme to forecast scores for items. The design of the URP algorithm relies heavily on the same users and considers that users who share the same tastes may enjoy similar items. ...
The recommendation system (RS) suffers badly from the cold start problem (CSP) that occurs due to the lack of sufficient information about the new customers, purchase history, and browsing data. Moreover, data sparsity problems also arise when the interaction is made among a limited number of items. These issues not only pose a negative impact on the recommendation but also significantly condense the diversity of choices available on the particular platform. To tackle these issues, a novel methodological approach called sparsity and cold start aware hybrid recommended system (SCSHRS) has been designed to suppress data sparsity and CSP in RS. The performance of the proposed SCSHRS method is tested on MovieLens-20 M, Last.FM and Book-Crossing data sets and compared with the prevailing techniques. Based on the evaluation reports with the standards, the proposed SCSHRS system gives Mean Absolute Percentage Error of 40%, and, precision (0.16), recall (0.08), F-measure (0.1), and Normalized Discounted Cumulative Gain of 0.65. This study completely describes the SCSHRS mechanism and its comparison with other pre-proposed historic and traditional processes based on collaborative filtering.
... It recommends items to users based on the ratings of similar users on various items and by predicting the missing ratings of the items [3,18]. CF is broadly classified as memory-based and model-based CF [25]. ...
Collaborative Filtering (CF) has intrigued several researchers whose goal is to enhance Recommender System’s performance by mitigating their drawbacks. CF’s common idea is to recognize user’s preferences by considering their ratings given to the items. The best-known limitations of recommender systems are the cpld start and data sparsity. In this paper, we analyse the CF-based recommendation approaches used to overcome the 2 issues, viz. cold start and data sparsity. This work attempts to implement the recommendation systems by 1) Generating a user-item similarity matrix and prediction matrix by performing collaborative filtering using memory-based CF approaches viz. KNNBasic, KNNBaseline, KNNWithMeans, SVD, and SVD++. 2) Generating a user-item similarity matrix and prediction matrix by performing collaborative filtering using model-based CF approach viz. Co-Clustering. The results reveal that the CF implemented using the K-NNBaseline approach decreased error rate when applied to MovieTrust datasets using cross-validation (CV = 5, 10, and 15). This approach is proved to address the cold start, sparsity issues and provide more relevant items as a recommendation.
... Singh et al. [27] presented a predictive approach called Z-Score, which considered the rating differences by converting the ratings to z-scores and calculating the weighted average of z-scores. A new User Rating Prediction (URP) [19] algorithm was proposed to predict ratings for items, which assumed that similar users may be interested in similar items. Alhijawi et al. [2] introduced a new adaptable prediction approach (INH-BP). ...
... Formally, our proposed prediction method is defined in Eq. (19), which improves the ability of prediction in sparse data by integrating more rating information of neighbors: ...
... Case 3: the similarity measure in case2 is still adopted to compute item similarity. The prediction method MC used above is replaced by the proposed prediction formula (19). ...
In memory-based collaborative filtering (CF) algorithms, the similarity and prediction method have a significant impact on the recommendation results. Most of the existing recommendation techniques have improved different similarity measures to alleviate inaccurate similarity results in sparse data, however, ignored the impact of sparse data on prediction results. To enhance the adaptability to sparse data, we propose a new item-based CF algorithm, which consists of the item similarity measure based vague sets and item-based prediction method with the new neighbor selection strategy. First, in the stage of similarity calculation, the Kullback–Leibler (KL) divergence based on vague sets is proposed from the perspective of user preference probability to measure item similarity. Following this, the impact of rating quantity is further considered to improve the accuracy of similarity results. Next, in the prediction stage, we relax the limit of depending on explicitly ratings and integrate more rating information to adjust prediction results. Experimental results on benchmark data sets show that, compared with other representative algorithms, our algorithm has better prediction and recommendation quality, and effectively alleviates the data sparseness problem.
... The advantages of the memory-based collaborative filtering algorithm are that the algorithm is easy to implement and has certain prediction accuracy and the recommended results have good interpretability [17,18]. However, this method also has significant disadvantages: it needs to maintain a similarity matrix, resulting in high computational overhead, difficult to deal with cold start and sparsity problems and poor scalability of the algorithm [19]. The modelbased collaborative filtering method can alleviate the sparsity problem [20]. ...
The rapid development of web technology has brought new problems and challenges to the recommendation system: on the one hand, the traditional collaborative filtering recommendation algorithm has been difficult to meet the personalized recommendation needs of users; on the other hand, the massive data brought by web technology provides more useful information for recommendation algorithms. How to extract features from this information, alleviate sparsity and dynamic timeliness, and effectively improve recommendation quality is a hot issue in the research of recommendation system algorithms. In view of the lack of an effective multisource information fusion mechanism in the existing research, an improved 5G multimedia precision marketing based on an improved multisensor node collaborative filtering recommendation algorithm is proposed. By expanding the input vector field, the features of users’ social relations and comment information are extracted and fused, and the problem of collaborative modelling of these two kinds of important auxiliary information is solved. The objective function is improved, the social regularization term and the internal regularization term in the vector domain are analysed and added from the perspective of practical significance and vector structure, which alleviates the overfitting problem. Experiments on a large number of real datasets show that the proposed method has higher recommendation quality than the classical and mainstream baseline algorithm.
... As a result, the ratings predicted by RPA may be partly incomplete. Kumar et al. [26] proposed a new user rating prediction (URP) algorithm that uses a fixed similarity algorithm. URP cannot transplant other commonly used similarity measurements, otherwise the recommendation performance of URP cannot be guaranteed. ...
... Kumar et al. [26] designed a new user rating prediction (URP) algorithm for predicting ratings of items. In URP, there is an assumption that if two users rate similar types of items and give similar ratings to these items, then these users are similar to each other. ...
... Our proposed IRP method is a kind of prediction rating algorithms, so we compare it with the existing rating prediction algorithms mentioned in the related work, including Sim-pred [24], Ave-pred [23], URP [26], and RPA [25]. Besides, we also compare with other NCF algorithms, such as Users' tree accessed on subspace (UTAOS) [31], Neighbor users by subspace clustering on collaborative filtering (NUSCCF) [32], and Collaborative filtering method based on the concept of "friend of a friend" (CFfoaf) [33]. ...
This paper investigates the issue of rating prediction for neighborhood-based collaborative filtering in recommendation systems. A novel rating prediction algorithm, called iterative rating prediction (IRP), is proposed for neighborhood-based collaborative filtering. The main idea behind IRP is neighborhood propagation. To predict ratings of items for target users, IRP relies on not only the rating information of direct neighbors but also that of indirect neighbors with different propagation depth. To implement the idea, IRP iteratively updates the ratings of items for users. The efficiency of the proposed method is examined through extensive experiments. Experimental results demonstrate the superior performance of our method, especially on small-scaled and sparse datasets.
... These two experiments produced very close results (less than 1% difference observed), hence, we report on the results from the first experiment, for conciseness. The practice described above is the typical one when evaluating a rating prediction CF algorithm [31,63,64]. ...
In this work, an algorithm for enhancing the rating prediction accuracy in collaborative filtering, which does not need any supplementary information, utilising only the users’ ratings on items, is presented. This accuracy enhancement is achieved by augmenting the importance of the opinions of ‘black sheep near neighbours’, which are pairs of near neighbours with opinion agreement on items that deviates from the dominant community opinion on the same item. The presented work substantiates that the weights of near neighbours can be adjusted, based on the degree to which the target user and the near neighbour deviate from the dominant ratings for each item. This concept can be utilized in various other CF algorithms. The experimental evaluation was conducted on six datasets broadly used in CF research, using two user similarity metrics and two rating prediction error metrics. The results show that the proposed technique increases rating prediction accuracy both when used independently and when combined with other CF algorithms. The proposed algorithm is designed to work without the requirements to utilise any supplementary sources of information, such as user relations in social networks and detailed item descriptions. The aforesaid point out both the efficacy and the applicability of the proposed work.
... Kumar et al. [31] suggested a User Rating Prediction (URP) scheme to forecast scores for items. The design of the URP algorithm relies heavily on the same users and considers that users who share the same tastes may enjoy similar items. ...
... F-measure: It reveals the accuracy of the experiment on the basis of precision and recall measure and is determined by Eqn. ) MAPE: It determines the percentage of deviation from the actual value and is computed using Eqn. vi) Accuracy: The accuracy of recommendation is determined by Eqn.(31). ...
Collaborative Filtering (CF) schemes are very popular in Recommender System (RS) and offer specialized suggestions to users in e-commerce and social websites. But, they suffer from the Cold Start Problem (CSP) that occurs due to the lack of sufficient information about the new customers, purchase history, and browsing data. Moreover, data sparsity problems may arise when the interaction is made among a limited amount of items. This not only poses a negative impact on recommendation but also significantly condenses the diversity of choices available in the particular platform. To tackle these issues, a novel methodological approach called Sparsity and Cold Start Aware Hybrid Recommended System (SCSHRS) is designed to suppress data sparsity and CSP in RS. The proposed SCSHRS methodology comprises four stages. At the initial stage, the data sparsity is reduced and at stage 2, the similar users are grouped by Ant-Lion based k-means clustering. At stage 3, Higher-Order Singular Value Decomposition (HOSVD) method decomposes the data to a lesser dimension. At the final stage, the Adaptive Neuro-Fuzzy Inference System (ANFIS) uses IF-THEN rules and machine learning abilities to predict the output. The performance of the proposed SCSHRS method is tested on MovieLens-20M, Last. FM, and Book-Crossing datasets and compared with the prevailing techniques. Based on the evaluation report, the proposed SCSHRS system gives Mean Absolute Percentage Error (MAPE) of 40%, and, precision (0.16), recall (0.08), F-measure (0.1), and Normalized Discounted Cumulative Gain (NDCD) of 0.65. Hence, SCSHRS is proved to be a more efficient means of recommendation against cold start and sparsity problems.
... Based on different types of filtering techniques, RS can be classified as shown in Fig. 1 (Siddiqui andAli 2017). Recommender systems have four filtering methods namely demographic filtering, collaborative filtering (CF), content-based filtering (CBF) and hybrid recommender systems (Cacheda et al. 2011;Ahn 2008;da Silva et al. 2018;Kumar et al. 2019). CF techniques take into consideration similarities between users or items while CBF techniques need domain knowledge to help generate recommendations. ...
... CBF technique is unable to handle the problem the following problems (da Silva et al. 2018;Kumar et al. 2019;Grčar et al. 2005): ...
These days users are able to save their time and effort by purchasing products online via various e-commerce websites. Their experience with a product exists in the form of textual reviews/feedbacks provided by them. Recommender systems offer personalized choices to users by capturing their interests and preferences. Through this paper identification of underlying topics using existing topic modeling techniques in user provided reviews of Moto e5 mobile on e-commerce website Amazon has been done and these techniques contrasted. Topic modeling is unsupervised learning technique used to identify hidden topics from a document (all the reviews of a product in this paper’s context). Coherence score, a measure of goodness of a topic reflecting the quality of human judgment compares these techniques. The higher the coherence score, the topic is more coherent. Experiments performed reveal that LDA technique performed better on the scrapped dataset.
... First, CF is applied to the user/item rating matrix, and the prediction matrix is generated. 28 Second, SVD, SVDþþ, Co-Clustering, KNNBasic, KNNBaseline, and KNNWithMeans approaches are applied to the predicted matrix, and the most relevant items are CF approaches learn a±nities between users and items based on previously collected user/item interaction data. Assuming two people give a similar opinion about an item, then they may have a similar item interest. ...
In recommender systems, Collaborative Filtering (CF) plays an essential role in promoting recommendation services. The conventional CF approach has limitations, namely data sparsity and cold-start. The matrix decomposition approach is demonstrated to be one of the effective approaches used in developing recommendation systems. This paper presents a new approach that uses CF and Singular Value Decomposition (SVD)[Formula: see text] for implementing a recommendation system. Therefore, this work is an attempt to extend the existing recommendation systems by (i) finding similarity between user and item from rating matrices using cosine similarity; (ii) predicting missing ratings using a matrix decomposition approach, and (iii) recommending top-N user-preferred items. The recommender system’s performance is evaluated considering Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Performance evaluation is accomplished by comparing the systems developed using CF in combination with six different algorithms, namely SVD, SVD[Formula: see text], Co-Clustering, KNNBasic, KNNBaseline, and KNNWithMeans. We have experimented using MovieLens 100[Formula: see text]K, MovieLens 1[Formula: see text]M, and BookCrossing datasets. The results prove that the proposed approach gives a lesser error rate when cross-validation ([Formula: see text]) is performed. The experimental results show that the lowest error rate is achieved with MovieLens 100[Formula: see text]K dataset ([Formula: see text], [Formula: see text]). The proposed approach also alleviates the sparsity and cold-start problems and recommends the relevant items.
