Collaborative filtering

About: Collaborative filtering is a research topic. Over the lifetime, 14771 publications have been published within this topic receiving 470440 citations.

Application of Item Response Theory to Collaborative Filtering

Abstract: Although many approaches to collaborative filtering have been proposed, few have considered the data quality of the recommender systems. Measurement is imprecise and the rating data given by users is true preference distorted. This paper describes how item response theory, specifically the rating scale model, may be applied to correct the ratings. The theoretically true preferences were then used to substitute for the actual ratings to produce recommendation. This approach was applied to the Jester dataset and traditional k-Nearest Neighbors (k-NN) collaborative filtering algorithm. Experiments demonstrated that rating scale model can enhance the recommendation quality of k-NN algorithm. Analysis also showed that our approach can predict true preferences which k-NN cannot do. The results have important implications for improving the recommendation quality of other collaborative filtering algorithms by finding out the true user preference first.

A trust-enhanced collaborative filtering recommender system

Abstract: Collaborative filtering(CF) strategy is widely used in recommender systems, but it also exists many weaknessses, for example:, chanages of preference and no user control of the system. In this paper, we propose a novel personalized strategy, which is used to deal with the weaknesses. On one part, a mechanism is introduced for user to manage his own trust relationship, which could increase user confidence for the system A Trust table is adopt for a single user to keep his own trust neighbors, trust degree can be changed or viewed. On another part trust value is used as a complementary factor to user similarity, which makes the recommendation more accurate, Experiment shows that the recommendation method has a better performance than traditional CF method, and it is believed to strengthen consumer confidence.

High Order Profile Expansion to tackle the new user problem on recommender systems.

Abstract: Collaborative Filtering algorithms provide users with recommendations based on their opinions, that is, on the ratings given by the user for some items. They are the most popular and widely implemented algorithms in Recommender Systems, especially in e-commerce, considering their good results. However, when the information is extremely sparse, independently of the domain nature, they do not present such good results. In particular, it is difficult to offer recommendations which are accurate enough to a user who has just arrived to a system or who has rated few items. This is the well-known new user problem, a type of cold-start. Profile Expansion techniques had been already presented as a method to alleviate this situation. These techniques increase the size of the user profile, by obtaining information about user tastes in distinct ways. Therefore, recommender algorithms have more information at their disposal, and results improve. In this paper, we present the High Order Profile Expansion techniques, which combine in different ways the Profile Expansion methods. The results show 110% improvement in precision over the algorithm without Profile Expansion, and 10% improvement over Profile Expansion techniques.

A Comparison Study of Model Based Collaborative Filtering Using Alternating Least Square and Singular Value Decomposition

Abstract: Recommender systems are systems that are built to recommend items to users based on a variety of criteria. These systems predict the most likely product that users are likely to buy and are interested in it. The most used recommender system is collaborative filtering. In this research, the author proposes determining the quality of the recommender system by comparing model-based collaborative filtering techniques, i.e., Alternating Least Squares and Singular Value Decomposition with three different characteristics dataset. This study showed Model-Based Collaborative Filtering (Alternating Least Squares and Singular Value Decomposition) able to improve the quality of the recommender system by considering the hyperparameter tuning result. Alternating Least Squares performs slightly better than Singular Value Decomposition in MovieLens and jester dataset.