Improved covering-based collaborative filtering for new users\u2019 personalized recommendations

Zhipeng Zhang,Yasuo Kudo,Tetsuya Murai,Yonggong Ren

doi:10.1007/s10115-020-01455-2

Abstract

User-based collaborative filtering (UBCF) is widely used in recommender systems (RSs) as one of the most successful approaches, but traditional UBCF cannot provide recommendations with satisfactory accuracy and diversity simultaneously. Covering-based collaborative filtering (CBCF) is a useful approach that we have proposed in our previous work, which greatly improves the traditional UBCF and could provide satisfactory recommendations to an active user which often has sufficient rating information. However, different from an active user, a new user in RSs often has special characteristics (e.g., fewer ratings or ratings concentrating on popular items), and the previous CBCF approach cannot provide satisfactory recommendations for a new user. In this paper, aiming to provide personalized recommendations for a new user, through a detailed analysis of the characteristics of new users, we reconstruct a decision class to improve the previous CBCF and utilize the covering reduction algorithm in covering-based rough sets to remove redundant candidate neighbors for a new user. Furthermore, unlike the previous CBCF, our improved CBCF could provide personalized recommendations without needing special additional information. Experimental results suggest that for the sparse datasets that often occur in real RSs, the improved CBCF significantly outperforms those of existing work and can provide personalized recommendations for a new user with satisfactory accuracy and diversity simultaneously.

Highlights

Rapid economic and technological development has led to people’s requirements becoming more personalized
Covering-based collaborative filtering (CBCF) is a useful approach, falling in the latter research line mentioned above, that we proposed in our previous work to improve accuracy and diversity of the traditional User-based collaborative filtering (UBCF) by utilizing covering-based rough sets [34,36]
Experimental results indicate that our improved CBCF can improve the accuracy metric, and increase the diversity of recommendations for a new user for the sort of sparse datasets that often occur in connection with real Recommender systems (RSs)

Summary

Introduction

Rapid economic and technological development has led to people’s requirements becoming more personalized. Recommender systems (RSs), which can recommend personalized objects (e.g., books, CDs, movies, and news), are widely used applications in daily life, for Web sites such as Amazon and Netflix. Their great commercial value and research potential have rendered RSs increasingly significant in recent years [3,4,16]. Most studies focus on developing new approaches to improve RS accuracy, it has been argued that using only an accuracy metric to evaluate RSs is not sufficient and that the diversity of recommendations must be considered as an important evaluation measure [6,7,13,17,29,32]. Recent studies have shown that it is very difficult to obtain a reasonable trade-off between the accuracy and diversity of an RS [20,37], because increasing the diversity of recommendations is usually accompanied by a loss in accuracy [14]

Objectives

Results

Discussion

Conclusion