Collaborative Filtering Recommendation Approach Research Articles

Federated against the cold: A trust-based federated learning approach to counter the cold start problem in recommendation systems

Recommendation systems are often challenged by the existence of cold-start items for which no previous rating is available. The standard content-based or collaborative-filtering recommendation approaches may address this problem by asking users to share their data with a central (cloud-based) server, which uses machine learning to predict appropriate ratings on such items. But users may be reluctant to have their (confidential) data shared. Federated learning has been lately capitalized on to address the privacy concerns by enabling an on-device distributed training of a single machine learning model. In this work, we propose a federated learning-based approach to address the item cold-start problem in recommendation systems. The originality of our solution compared to existing federated learning-based solutions comes from (1) applying federated learning specifically to the cold-start problem; (2) proposing a trust mechanism to derive trust scores for the potential recommenders, followed by a double deep Q learning scheduling approach that relies on the trust and energy levels of the recommenders to select the best candidates. Simulations on the MovieLens 1M and Epinions datasets suggest that our solution improves the accuracy of recommending cold-start items and reduces the RMSE, MAE and running time compared to five benchmark approaches.

New Strategy Based on RBF Network to Develop a Collaborative Filtering Recommender System

Collaborative filtering is a popular recommendation algorithm. It predicts user's interests according to the ratings or behaviour of other users in the system. However, the collaborative filtering recommender system suffers from several major limitations including scalability, sparsity, and cold start. In this paper, a collaborative filtering recommendation approach using radial basis function (RBF) network and power method is proposed. The proposed system has offline and online phases. In the offline phase, the sparse user-item rating matrix is completed by using RBF network based on Cover's theorem on the separability of patterns. RBF network learning is done by unsupervised kernel-based fuzzy c-means clustering algorithm for selecting RBF centers, and supervised gradient descend method for selecting RBF weights. In the offline phase, we predict non-rated items of a user. Then the full rating matrix is used to rank all the users. The ranking is done by solving an eigenvalue problem. This paper overcomes the scalability problem by clustering the users, the sparsity problem by completing the sparse rating matrix, and the new user cold start problem by recommending the top rated items of the high-ranked user. The results of the experiments, on the benchmark data sets, show that the proposed system produces high quality recommendation, in terms of accuracy and quality.

Recommendation Algorithm in Double-Layer Network Based on Vector Dynamic Evolution Clustering and Attention Mechanism

The purpose of recommendation systems is to help users find effective information quickly and conveniently and also to present the items that users are interested in. While the literature of recommendation algorithms is vast, most collaborative filtering recommendation approaches attain low recommendation accuracies and are also unable to track temporal changes of preferences. Additionally, previous differential clustering evolution processes relied on a single-layer network and used a single scalar quantity to characterise the status values of users and items. To address these limitations, this paper proposes an effective collaborative filtering recommendation algorithm based on a double-layer network. This algorithm is capable of fully exploring dynamical changes of user preference over time and integrates the user and item layers via an attention mechanism to build a double-layer network model. Experiments on Movielens, CiaoDVD, and Filmtrust datasets verify the effectiveness of our proposed algorithm. Experimental results show that our proposed algorithm can attain a better performance than other state-of-the-art algorithms.

An Intelligent Data Analysis for Recommendation Systems Using Machine Learning

In recent times, selection of a suitable hotel location and reservation of accommodation have become a critical issue for the travelers. The online hotel search has been increased at a very fast pace and became very time-consuming due to the presence of huge amount of online information. Recommender systems (RSs) are getting importance due to their significance in making decisions and providing detailed information about the required product or a service. To acquire the hotel recommendations while dealing with textual hotel reviews, numerical ranks, votes, ratings, and number of video views have become difficult. To generate true recommendations, we have proposed an intelligent approach which also deals with large-sized heterogeneous data to fulfill the needs of the potential customers. The collaborative filtering (CF) approach is one of the most popular techniques of the RS to generate recommendations. We have proposed a novel CF recommendation approach in which opinion-based sentiment analysis is used to achieve hotel feature matrix by polarity identification. Our approach combines lexical analysis, syntax analysis, and semantic analysis to understand sentiment towards hotel features and the profiling of guest type (solo, family, couple etc). The proposed system recommends hotels based on the hotel features and guest type for personalized recommendation. The developed system not only has the ability to handle heterogeneous data using big data Hadoop platform but it also recommends hotel class based on guest type using fuzzy rules. Different experiments are performed over the real-world datasets obtained from two hotel websites. Moreover, the values of precision and recall and F-measure have been calculated, and the results are discussed in terms of improved accuracy and response time, significantly better than the traditional approaches.

A recommender system for selecting potential industrial training organizations

The difficulty in securing students industrial work experience scheme (SIWES) placements has negatively affected the final grades of some undergraduates. A recommender system is hereby proposed to solve this problem. This system will use past SIWES data to recommend potential organizations to future SIWES students. Research data collection was through an online questionnaire, with 200 respondents. The data was divided into a training data set (70%) and test data set (30%). Collaborative filtering recommendation approach was employed using the C4.5 algorithm to classify the data and generate a decision tree model from the training data set. The model generated was used to predict the class label of the test data set. Results from the data analysis carried out revealed that Kappa statistics was 0.7839, mean absolute error = 0.0058, and root mean squared error = 0.0586. In addition, true positive rate = 0.788, recall = 0.788, precision = 0.749, F‐measure = 0.755, MCC = 0.760, ROC = 0.985, and PRC = 0.813. The high values obtained indicates that the model was predicting with a high level of accuracy, ie, 78.84% correctly classified instances. The developed model was used as a knowledge base to develop a very beneficial front‐end web application, tagged “RecommendIT” where students can enter their preferences and view company recommendations.

From similarity perspective: a robust collaborative filtering approach for service recommendations

Collaborative filtering (CF) is a technique commonly used for personalized recommendation and Web service quality-of-service (QoS) prediction. However, CF is vulnerable to shilling attackers who inject fake user profiles into the system. In this paper, we first present the shilling attack problem on CF-based QoS recommender systems for Web services. Then, a robust CF recommendation approach is proposed from a user similarity perspective to enhance the resistance of the recommender systems to the shilling attack. In the approach, the generally used similarity measures are analyzed, and the DegSim (the degree of similarities with top k neighbors) with those measures is selected for grouping and weighting the users. Then, the weights are used to calculate the service similarities/differences and predictions.We analyzed and evaluated our algorithms using WS-DREAM and Movielens datasets. The experimental results demonstrate that shilling attacks influence the prediction of QoS values, and our proposed features and algorithms achieve a higher degree of robustness against shilling attacks than the typical CF algorithms.

Factorization-based primary dimension modelling for multidimensional data in recommender systems

In recent years, multidimensional data is becoming increasingly popular in recommender systems. For example, social tagging systems encourage users to employ user-defined keywords to help manage content in a personalized way. Recommender systems built upon social tagging systems utilize social tagging data to improve recommendation accuracy. Context-aware recommender systems incorporate context information (e.g. time, location, weather, etc.) into recommendation models to make recommendations more personalized. User profiles play a crucial role in recommender systems because user profiles provide the information about users’ information needs based on which personalized recommendations can be generated. Existing user profiling techniques for collaborative filtering (CF) recommender systems based on multidimensional data mostly analyze data through splitting the multidimensional relations into lower-dimensional relations. However, this leads to the loss of multidimensionality in user-item interactions. A different type of methods for addressing multidimensional data is factorization techniques such as tensor factorization (TF), which discover holistic latent relations between all dimensions in multidimensional data. However, TF models are not constructed to analyze any particular dimension of multidimensional data. But for many application domains, certain dimensions are of particular interest such as the user dimension in recommender systems. However, user profiles are not explicitly reflected in TF models. In this paper, we propose a unified approach to profile any particular dimension in multidimensional data based on partially-decomposed Tucker models (TM). We prove that the proposed profiling approach is a compatible higher-order extension of the matrix factorization based approaches. Moreover, we prove that the proposed TM-based profiles can be updated incrementally with new data without reconstructing the entire profiles. We integrate the proposed TF-based user/item profiling approach into neighborhood-based collaborative filtering recommenders for making top-N item recommendations. Extensive experiments have been conducted using real-world social tagging datasets to demonstrate that the CF recommenders integrated with the proposed user/item profiles outperform state-of-the-art CF recommendation approaches in terms of recommendation accuracy.

A PageRank-based collaborative filtering recommendation approach in digital libraries

A PageRank-based collaborative filtering recommendation approach in digital libraries

A recommendation approach for programming online judges supported by data preprocessing techniques

The use of programming online judges (POJ) to support students acquiring programming skills is common nowadays because this type of software contains a large collection of programming exercises to be solved by students. A POJ not only provides exercises but also automates the code compilation and its evaluation process. A common problem that students face when using POJ is information overload, as choosing the right problem to solve can be quite frustrating due to the large number of problems offered. The integration of current POJs into e-learning systems such as Intelligent Tutoring Systems (ITSs) is hard because of the lack of necessary information in ITSs. Hence, the aim of this paper is to support students with the information overload problem by using a collaborative filtering recommendation approach that filters out programming problems suitable for students’ programming skills. It uses an enriched user-problem matrix that implies a better student role representation, facilitating the computation of closer neighborhoods and hence a more accurate recommendation. Additionally a novel data preprocessing step that manages anomalous users’ behaviors that could affect the recommendation generation is also integrated in the recommendation process. A case study is carried out on a POJ real dataset showing that the proposal outperforms other previous approaches.

Collaborative Filtering with Entropy-Driven User Similarity in Recommender Systems

Collaborative filtering (CF) is the most popular approach in personalized recommender systems. Although CF approaches have successfully been used and have the advantage in that it is unnecessary to analyze item content when generating recommendations, they nevertheless suffer from problems with accuracy. In this paper, we propose a new CF approach to improve recommendation performance. First, a new information entropy-driven user similarity measure model is proposed to measure the relative difference between ratings. A Manhattan distance-based model is then developed to address the fat tail problem by estimating the alternative active user average rating. The effectiveness of the proposed approach is analyzed on public and private data sets. As a result of the introduction of the new similarity measure and average rating estimation, we demonstrate that the proposed new CF recommendation approach provides better recommendations.

Clustering- and regression-based multi-criteria collaborative filtering with incremental updates

Recommender systems are a valuable means for online users to find items of interest in situations when there exists a large set of alternatives. Collaborative Filtering (CF) is a popular technique to build such systems which is based on explicit rating feedback on the items by a larger user community. Recent research has demonstrated that the predictive accuracy of CF based recommender systems can be measurably improved when multi-criteria ratings are available, i.e., when users provide ratings for different aspects of the recommendable items. Technically, in particular regression-based techniques have been shown to be a promising means to predict the user’s overall assessment of an item based on the multi-criteria ratings.Since in many domains customer subgroups (segments) exist that share similar preferences regarding the item features, we propose a novel CF recommendation approach in which such customer segments are automatically detected through clustering and preference models are learned for each customer segment. In addition, since in practical application constantly new rating information is available, the proposed method supports incremental updates of the preference models. An empirical evaluation of our method shows that the predictions of the resulting models are more accurate than previous multi-criteria recommendation methods.

A Collaborative Filtering Recommendation Approach Based on User Rating Similarity and User Attribute Similarity

With the speedy development of network, information technology has provided an unmatched amount of information resources. It has also led to the problem of information overload. However, people experiences and knowledge often do not enough to process the vast amount of usable information. Thus, approaches to help find resources of interest have attracted much attention from researchers. And recommender systems have arrived to solve this problem. Recommender system plays an important role mainly in an electronic commerce environment as a new marketing strategy. Although a varied of recommendation techniques has been developed recently, collaborative filtering has been known to be the most successful recommendation techniques and has been used in a number of different applications. But traditional collaborative filtering recommendation algorithm has the problem of sparsity. Aiming at the problem of data sparsity for personalized filtering systems, a collaborative filtering recommendation algorithm based on user rating similarity and user attribute similarity is given. This approach not only considers the user item rating information, but also takes into account the user attribute.

A Novel Collaborative Filtering Recommendation Approach Based on Field Authorities

This paper presents a novel collaborative filtering recommendation algorithm based on field authorities which simulates the real life word of mouth recommendation mode. It uses the specialistic knowledge from field authorities of different genres, and successfully addresses data sparsity and noise problems existing in traditional collaborative filtering. Meanwhile it also improves prediction accuracy and saves computational overhead effectively. Experiments on MovieLens datasets show that the accuracy of our algorithm is significantly higher than collaborative filtering approach based on experts, and has larger scope because of no external data limitations. Meanwhile, compared to traditional k-NN collaborative filtering, our algorithm has a better performance both in MAE and precision experiments, and the computational overhead has a decrease of 19.2% while they provide the same accuracy level.

MINGLING THE CONTEXTUAL INFORMATION IN IMPROVED MULTIDIMENSIONAL RECOMMENDATION SYSTEM

Recommender systems utilize the times of yore experiences and preferences of the target customers as a basis to proffer personalized recommendations for them as well as resolve the information overloading hitch. Personalized recommendation methods are primarily classified into content-based recommendation approach and collaborative filtering recommendation approach. Both recommendation approaches have their own advantages, drawbacks and complementarities. Because conventional recommendation techniques don’t consider the contextual information, the real factor why a customer likes a specific product is unable to be understood. Therefore, in reality, it often causes a decrease in the accuracy of the recommendation results and also persuades the recommendation quality. In this paper, we propose the integrated contextual information as the foundation concept of multidimensional recommendation model and use the Online Analytical Processing (OLAP) ability of data warehousing to solve the contradicting tribulations among hierarchy ratings. This work hopes that by establishing additional user profiles and multidimensional analysis to find the key factors affecting user perceptions, it would increase the recommendation quality.

A hybrid trust-enhanced collaborative filtering recommendation approach for personalized government-to-business e-services

The information overload on the World Wide Web results in the underuse of some existing e-government services within the business domain. Small-to-medium businesses (SMBs), in particular, are seeking “one-to-one'' e-services from government in current highly competitive markets, and there is an imperative need to develop Web personalization techniques to provide business users with information and services specific to their needs, rather than an undifferentiated mass of information. This paper focuses on how e-governments can support businesses on the problem of selecting a trustworthy business partner to perform reliable business transactions. In the business partner selection process, trust or reputation information is crucial and has significant influence on a business user's decision regarding whether or not to do business with other business entities. For this purpose, an intelligent trust-enhanced recommendation approach to provide personalized government-to-business (G2B) e-services, and in particular, business partner recommendation e-services for SMBs is proposed. Accordingly, in this paper, we develop (1) an implicit trust filtering recommendation approach and (2) an enhanced user-based collaborative filtering (CF) recommendation approach. To further exploit the advantages of the two proposed approaches, we develop (3) a hybrid trust-enhanced CF recommendation approach (TeCF) that integrates both the proposed implicit trust filtering and the enhanced user-based CF recommendation approaches. Empirical results demonstrate the effectiveness of the proposed approaches, especially the hybrid TeCF recommendation approach in terms of improving accuracy, as well as in dealing with very sparse data sets and cold-start users. © 2011 Wiley Periodicals, Inc. © 2011 Wiley Periodicals, Inc.

A Personalized Recommender Systems Framework Based on Ontology and Bayesian Network in E-Commerce

Personalized recommendation methods are mainly classified into content-based recommendation approach and collaborative filtering recommendation approach. However, Both recommendation approaches have their own drawbacks such as sparsity, cold-start and scalability. To overcome the drawbacks, In this paper, we propose a framework for recommender systems that join use of Ontology and Bayesian Network. On the one hand, Ontology help formally defining the semantics of variables included in the Bayesian network, thus allowing logical reasoning on them. On the other hand, Bayesian network allow reasoning under uncertainty, that is not possible only with the use of ontology. In the recommendation, products not yet purchased or rarely purchased can still be recommended to customers with accuracy.

Using contextual information and multidimensional approach for recommendation

It has been recognized that recommendation system is a very important and indispensable topic in E-commerce. Many famous E-commerce websites utilize recommendation systems to convert browsers into buyers. The forms of recommendation include suggesting products/services to the customer, providing personalized product/service information, summarizing community opinion, and providing community critiques. Personalized recommendation methods are mainly classified into content-based recommendation approach and collaborative filtering recommendation approach. Both recommendation approaches, however, have their own drawbacks. This study proposes the integrated contextual information as the foundation concept of multidimensional recommendation model, and uses the online analytical processing (OLAP) ability of data warehousing to solve the contradicting problems among hierarchy ratings. The evaluation studies show that by establishing additional customer profiles and using multidimensional analyses to find the key factors affecting customer perceptions, the proposed approach increases the recommendation quality.