Collaborative Filtering Approach Research Articles

JacUOD: A New Similarity Measurement for Collaborative Filtering

Collaborative filtering (CF) has been widely applied to recommender systems, since it can assist users to discover their favorite items. Similarity measurement that measures the similarity between two users or items is critical to CF. However, traditional similarity measurement approaches for memory-based CF can be strongly improved. In this paper, we propose a novel similarity measurement, named Jaccard Uniform Operator Distance (JacUOD), to effectively measure the similarity. Our JacUOD approach aims at unifying similarity comparison for vectors in different multidimensional vector spaces. Compared with traditional similarity measurement approaches, JacUOD properly handles dimension-number difference for different vector spaces. We conduct experiments based on the well-known MovieLens datasets, and take user-based CF as an example to show the effectiveness of our approach. The experimental results show that our JacUOD approach achieves better prediction accuracy than traditional similarity measurement approaches.

Collaborative filtering based on information-theoretic co-clustering

Collaborative filtering is one of the most popular recommendation techniques, which provides personalised recommendations based on users’ tastes. In spite of its huge success, it suffers from a range of problems, the most fundamental being that of data sparsity. Sparsity in ratings makes the formation of inaccurate neighbourhood, thereby resulting in poor recommendations. To address this issue, in this article, we propose a novel collaborative filtering approach based on information-theoretic co-clustering. The proposed approach computes two types of similarities: cluster preference and rating, and combines them. Based on the combined similarity, the user-based and item-based approaches are adopted, respectively, to obtain individual predictions for an unknown target rating. Finally, the proposed approach fuses these resultant predictions. Experimental results show that the proposed approach is superior to existing alternatives.

평가의 시간 순서를 고려한 강화 학습 기반 협력적 여과

In recent years, there has been increasing interest in recommender systems which provide users with personalized suggestions for products or services. In particular, researches of collaborative filtering analyzing relations between users and items has become more active because of the Netflix Prize competition. This paper presents the reinforcement learning approach for collaborative filtering. By applying reinforcement learning techniques to the movie rating, we discovered the connection between a time sequence of past ratings and current ratings. For this, we first formulated the collaborative filtering problem as a Markov Decision Process. And then we trained the learning model which reflects the connection between the time sequence of past ratings and current ratings using Q-learning. The experimental results indicate that there is a significant effect on current ratings by the time sequence of past ratings.

A hybrid online-product recommendation system: Combining implicit rating-based collaborative filtering and sequential pattern analysis

Many online shopping malls in which explicit rating information is not available still have difficulty in providing recommendation services using collaborative filtering (CF) techniques for their users. Applying temporal purchase patterns derived from sequential pattern analysis (SPA) for recommendation services also often makes users unhappy with the inaccurate and biased results obtained by not considering individual preferences. The objective of this research is twofold. One is to derive implicit ratings so that CF can be applied to online transaction data even when no explicit rating information is available, and the other is to integrate CF and SPA for improving recommendation quality. Based on the results of several experiments that we conducted to compare the performance between ours and others, we contend that implicit rating can successfully replace explicit rating in CF and that the hybrid approach of CF and SPA is better than the individual ones.

User-Weight Model for Item-based Recommendation Systems

Nowadays, item-based Collaborative Filtering (CF) has been widely used as an effective way to help people cope with information overload. It computes the item-item similarities/differentials and then selects the most similar items for prediction. A weakness of current typical item-based CF approaches is that all users have the same weight in computing the item relationships. In order to improve the recommendation quality, we incorporate users’ weights based on a relationship model of users into item similarities and differentials computing. In this paper, a model of user relationship, a method for computing users’ weights, and weight-based item-item similarities/differentials computing approaches are proposed for item-based CF recommendations. Finally, we experimentally evaluate our approach for recommendation and compare it to typical item-based CF approaches based on Adjusted Cosine and Slope One. The experiments show that our approaches can improve the recommendation results of them.

Context-Aware Expert Finding in Tag Based Knowledge Sharing Communities

With the rapid development of online Knowledge Sharing Communities (KSCs), the problem of finding experts becomes increasingly important for knowledge propagation and putting crowd wisdom to work. A recent development trend of KSCs is to allow users to add text tags for annotating their posts, which are more accurate than traditional category information. However, how to leverage these user-generated tags for finding experts is still underdeveloped. To this end, this paper develops a novel approach for finding experts in tag based KSCs by leveraging tag context and the semantic relationship between tags. Specifically, the extracted prior knowledge and user profiles are first used for enriching the query tags to infer tag context, which represents the user’s latent information needs. Specifically, two different approaches for addressing the problem of tag sparseness in authority ranking are proposed. The first is a memory-based collaborative filtering approach, which leverages non-negative matrix factorization (NMF) to find similar users for alleviating tag sparseness. The second approach is based on Latent Dirichlet Allocation (LDA) topic model, which can further capture the latent semantic relationship between tags. A large-scale real-world data set is collected from a tag based Chinese commercial Q&A web site. Experimental results show that the proposed method outperforms several baseline methods with a significant margin.

Enhancing Collaborative Filtering by User Interest Expansion via Personalized Ranking

Recommender systems suggest a few items from many possible choices to the users by understanding their past behaviors. In these systems, the user behaviors are influenced by the hidden interests of the users. Learning to leverage the information about user interests is often critical for making better recommendations. However, existing collaborative-filtering-based recommender systems are usually focused on exploiting the information about the user's interaction with the systems; the information about latent user interests is largely underexplored. To that end, inspired by the topic models, in this paper, we propose a novel collaborative-filtering-based recommender system by user interest expansion via personalized ranking, named iExpand. The goal is to build an item-oriented model-based collaborative-filtering framework. The iExpand method introduces a three-layer, user-interests-item, representation scheme, which leads to more accurate ranking recommendation results with less computation cost and helps the understanding of the interactions among users, items, and user interests. Moreover, iExpand strategically deals with many issues that exist in traditional collaborative-filtering approaches, such as the overspecialization problem and the cold-start problem. Finally, we evaluate iExpand on three benchmark data sets, and experimental results show that iExpand can lead to better ranking performance than state-of-the-art methods with a significant margin.

An implementation and evaluation of recommender systems for traveling abroad

The improvement of information technology makes storage no longer a problem. In addition, the birth of the Internet makes information transfer faster than ever. It brings us convenient life. However, more and more information result in a new problem, which is information overload. Today, many more people are traveling abroad since they no longer have to work on weekends. Traveling abroad has become a kind of trend. There are more than a hundred countries in the world worth to travel, and there is so much information available that it makes a traveler’s decision extremely difficult to make. In our research, we try to implement the most common three kinds of recommender system techniques in order to recommend to customers which countries are the best traveling locations for them. Thus, we can save travelers a lot of time when deciding where to go. From our experiment and evaluation, we find that a hybrid recommender system is a better technique in recommendation according to our abroad database, and it conquers the shortcomings of content-based filtering and collaborative filtering approaches.

Learning bidirectional asymmetric similarity for collaborative filtering via matrix factorization

Memory-based collaborative filtering (CF) aims at predicting the rating of a certain item for a particular user based on the previous ratings from similar users and/or similar items. Previous studies in finding similar users and items have several drawbacks. First, they are based on user-defined similarity measurements, such as Pearson Correlation Coefficient (PCC) or Vector Space Similarity (VSS), which are, for the most part, not adaptive and optimized for specific applications and data. Second, these similarity measures are restricted to symmetric ones such that the similarity between A and B is the same as that for B and A, although symmetry may not always hold in many real world applications. Third, they typically treat the similarity functions between users and functions between items separately. However, in reality, the similarities between users and between items are inter-related. In this paper, we propose a novel unified model for users and items, known as Similarity Learning based Collaborative Filtering (SLCF) , based on a novel adaptive bidirectional asymmetric similarity measurement. Our proposed model automatically learns asymmetric similarities between users and items at the same time through matrix factorization. Theoretical analysis shows that our model is a novel generalization of singular value decomposition (SVD). We show that, once the similarity relation is learned, it can be used flexibly in many ways for rating prediction. To take full advantage of the model, we propose several strategies to make the best use of the proposed similarity function for rating prediction. The similarity can be used either to improve the memory-based approaches or directly in a model based CF approaches. In addition, we also propose an online version of the rating prediction method to incorporate new users and new items. We evaluate SLCF using three benchmark datasets, including MovieLens, EachMovie and Netflix, through which we show that our methods can outperform many state-of-the-art baselines.

Userrank for item-based collaborative filtering recommendation

With the recent explosive growth of the Web, recommendation systems have been widely accepted by users. Item-based Collaborative Filtering (CF) is one of the most popular approaches for determining recommendations. A common problem of current item-based CF approaches is that all users have the same weight when computing the item relationships. To improve the quality of recommendations, we incorporate the weight of a user, userrank, into the computation of item similarities and differentials. In this paper, a data model for userrank calculations, a PageRank-based user ranking approach, and a userrank-based item similarities/differentials computing approach are proposed. Finally, the userrank-based approaches improve the recommendation results of the typical Adjusted Cosine and Slope One item-based CF approaches.

Collaborative user modeling for enhanced content filtering in recommender systems

Recommender systems, which have emerged in response to the problem of information overload, provide users with recommendations of content suited to their needs. To provide proper recommendations to users, personalized recommender systems require accurate user models of characteristics, preferences and needs. In this study, we propose a collaborative approach to user modeling for enhancing personalized recommendations to users. Our approach first discovers useful and meaningful user patterns, and then enriches the personal model with collaboration from other similar users. In order to evaluate the performance of our approach, we compare experimental results with those of a probabilistic learning model, a user model based on collaborative filtering approaches, and a vector space model. We present experimental results that show how our model performs better than existing alternatives.

Collaborative user modeling with user-generated tags for social recommender systems

With the popularity of social media services, the sheer amount of content is increasing exponentially on the Social Web that leads to attract considerable attention to recommender systems. Recommender systems provide users with recommendations of items suited to their needs. To provide proper recommendations to users, recommender systems require an accurate user model that can reflect a user’s characteristics, preferences and needs. In this study, by leveraging user-generated tags as preference indicators, we propose a new collaborative approach to user modeling that can be exploited to recommender systems. Our approach first discovers relevant and irrelevant topics for users, and then enriches an individual user model with collaboration from other similar users. In order to evaluate the performance of our model, we compare experimental results with a user model based on collaborative filtering approaches and a vector space model. The experimental results have shown the proposed model provides a better representation in user interests and achieves better recommendation results in terms of accuracy and ranking.

From Community Detection to Mentor Selection in Rating-Free Collaborative Filtering

The number of items that users can now access when navigating on the Web is so huge that these might feel lost. Recommender systems are a way to cope with this profusion of data by suggesting items that fit the users needs. One of the most popular techniques for recommender systems is the collaborative filtering approach that relies on the preferences of items expressed by users, usually under the form of ratings. In the absence of ratings, classical collaborative filtering techniques cannot be applied. Fortunately, the behavior of users, such as their consultations, can be collected. In this paper, we present a new approach to perform collaborative filtering when no rating is available but when user consultations are known. We propose to take inspiration from local community detection algorithms to form communities of users and deduce the set of mentors of a given user. We adapt one state-of-the-art algorithm so as to fit the characteristics of collaborative filtering. Experiments conducted show that the precision achieved is higher then the baseline that does not perform any mentor selection. In addition, our model almost offsets the absence of ratings by exploiting a reduced set of mentors.

A Collaborative Filtering Approach to Making Recommendations Based on Ontology in the Movie Domain

A Collaborative Filtering Approach to Making Recommendations Based on Ontology in the Movie Domain

A Collaborative Filtering Recommendation Algorithm Based on Time Weight

Personalized recommendation systems are web-based systems that aim at predicting a user’s interest on available products and services by relying on previously rated items and dealing with the problem of information and product overload. Collaborative filtering algorithm is one of the most successful technologies for building personalized recommendation system. But traditional collaborative filtering algorithm does not consider the problem of drifting users interests and the nearest neighbor user set in different time periods, leading to the fact that neighbors may not be the nearest set. In view of this problem, a collaborative filtering recommendation algorithm based on time weight is presented. In the algorithm each rating is assigned a weight gradually decreasing along with time and the weighted rating is used to produce recommendation. The collaborative filtering approach based on time weight not only reduced the data sparsity, but also narrowed the area of the nearest neighbor.

The role of user mood in movie recommendations

Studies in consumer research indicate that mood states have effects on user behaviors and evaluation. In movie recommendation, a user in a bad mood might decide to rate some movies more harshly. In this paper, we examine how users’ mood can have an impact on their appraisal of movies in different genres, which in turn can help inform recommender system of picking up movies that are appropriate for users in different mood. Specifically, we carried out two studies. The first consists of a series of user studies to examine user mood and movie ratings to answer questions like: will a user in a more positive mood tend to rate a romantic comedy higher? Will a user in a more nervous mood tend to rate an action movie higher? Then, drawn upon the results from the first study, we modify the traditional collaborative-filtering based recommendation approach by injecting user mood and proposed a mood-aware collaborative-filtering approach. Empirical studies demonstrate that the mood-aware recommendation approach performs better than traditional one that does not consider mood.

ICRS: an intelligent collaborative recommender system for electronic purchasing

Finding the right product that satisfies the user's needs and wants in e-purchasing is a challenging problem. We design and implement an Intelligent Collaborative Recommender System (ICRS) to map users' needs to the products that can satisfy them. A methodology is used to dynamically update the accuracy factor based on user intelligence. The different approaches for recommendation are categorised as memory-based and model-based approaches. Memory-based systems suffer from data sparsity and scalability problems, whereas model-based approaches tend to limit the range of users. Hence, by integrating both these approaches, we overcome the shortfalls. In our paper, we smooth the sparse data and apply the collaborative filtering approach for recommendations. Recommendations are made more accurate by applying regression to weighted aggregated predictions. The system that is considered here is the book recommendation system. The metric that is considered for measuring the performance of our system is the Mean Absolute Error (MAE). In terms of the computation time, clustering similar users is done offline, which greatly reduces the time for computation. This approach thus alleviates scalability and sparsity problems and offers accurate recommendations. Finally, our system is developed for an online book purchasing application and tested by our college students.

A recommendation algorithm based on users’ partial similarity

Collaborative filtering is one of the most successful techniques for building recommender systems, and is extensively used in many personalized systems. However, existing collaborative filtering algorithms have been suffering from data sparsity and low recommendation accuracy problems. This paper focused the collaborative filtering problems on two crucial steps: (1) computing neighbor users for active users and (2) missing data prediction algorithm. Consequently, this paper proposed an improved collaborative filtering algorithm based on Users' Partial Similarity (CFUPS for short), which computed the similarity between users relying on partial items with their common interests, not on all common rated items. Besides, it combined items' attributes similarity and their ratings similarity properly as a weight for computing missing ratings. Theoretically, our method is effective in improving the recommendation precision and withstanding data sparsity. In the meantime, the experimental results show that our proposed CFUPS algorithm outperforms other existing collaborative filtering approaches.

Collaborative filtering with interlaced generalized linear models

Collaborative filtering (CF) is a data analysis task appearing in many challenging applications, in particular data mining in Internet and e-commerce. CF can often be formulated as identifying patterns in a large and mostly empty rating matrix. In this paper, we focus on predicting unobserved ratings. This task is often a part of a recommendation procedure. We propose a new CF approach called interlaced generalized linear models (GLM); it is based on a factorization of the rating matrix and uses probabilistic modeling to represent uncertainty in the ratings. The advantage of this approach is that different configurations, encoding different intuitions about the rating process can easily be tested while keeping the same learning procedure. The GLM formulation is the keystone to derive an efficient learning procedure, applicable to large datasets. We illustrate the technique on three public domain datasets.

Online shopping recommendation mechanism and its influence on consumer decisions and behaviors: A causal map approach

Purpose of this paper: Online product recommendation mechanism (agents) are becoming increasingly available on websites to assist consumers with reducing information overload, provide advice in finding suitable products, and facilitate online consumer decision-making. Central of these services is consumers' satisfaction with recommendation results. Traditional recommendation mechanism (TRM) is based content and/or collaborative filtering approach. However, the remaining problem concerning TRM is how to analyze the causal relationships between quantitative and qualitative factors, and investigate their impact on the central routes and peripheral routes through which both quantitative and qualitative factors can affect customer online shopping decisions. It is well known that qualitative factors are hard to codify yet they have a significant effect on a customer's decision-making process in the form of causal relationships with quantitative factors. Thus, a new online recommendation mechanism is required that incorporates qualitative factors systematically with quantitative factors to analyze their combined influence on customers' purchasing decision-making process. So, our study suggest that causal maps based recommendation mechanism (CMRM). Design/methodology/approach: ELM was applied to build hypotheses concerning how consumers' decision satisfaction and online shopping behavior are affected by CMRM. Specifically, the performance of the proposed CMRM is analyzed empirically by garnering the experiment data from 250 qualified respondents who were asked to refer to the proposed CMRM before making purchasing decisions on mobile phones. Findings: Statistical results proved that the proposed CMRM could enhance consumers' decision satisfaction, attitude towards the recommended products, as well as positive purchase intentions and actual purchase. Practical implications: CMRM can be easily implemented on the web, allowing target consumers to experience a real recommendation process. And, a wide variety of qualitative factors that seem crucial to most consumers can be pre-defined through a survey, and incorporated into causal maps. Thus, such causal maps will improve the personalization effect on the target consumer's purchase intentions.