A Kind of Collaborative Filtering Algorithm Based on User Clustering and Time Stamp

DOI

10.2991/isaeece-16.2016.39How to use a DOI?

Keywords

Collaborative filtering; user clustering; time stamp; user recommendation

Abstract

In the case of user rating data is very large and sparse, the effect of traditional collaborative filtering algorithm in use recommendation is unsatisfactory. In this paper, a collaborative filtering algorithm based on user clustering and time stamp is proposed. Which first clusters the users according to user’s preferences for different types of items, thus user will only recommended items to members belong to his/her own cluster, thus can largely reduce the input data of recommendation algorithm, and can improve recommendation effectiveness. Then taking account the factor that user will change his/her interest, in the traditional collaborative filtering algorithm, time factor is added to realize a real-time user recommendation. Experimental results show that the proposed algorithm can improve the accuracy and recall rate of user recommendation.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shuqin Li
AU  - Xiaohua Yuan
AU  - Huaimei Han
PY  - 2016/04
DA  - 2016/04
TI  - A Kind of Collaborative Filtering Algorithm Based on User Clustering and Time Stamp
BT  - Proceedings of the 2016 International Symposium on Advances in Electrical, Electronics and Computer Engineering
PB  - Atlantis Press
SP  - 200
EP  - 205
SN  - 2352-5401
UR  - https://doi.org/10.2991/isaeece-16.2016.39
DO  - 10.2991/isaeece-16.2016.39
ID  - Li2016/04
ER  -