Algorithm optimization of recommendation based on probabilistic matrix factorization

DOI

10.2991/icmmita-16.2016.306How to use a DOI?

Keywords

Recommendation system;Probabilistic matrix factorization;User-trust network;Stochastic gradient descent.

Abstract

With the rapid development of the internet, the excessive information of user and item leads to user-item rating matrix becomes bigger and more sparse, also, accuracy of the traditional collaborative filtering recommendation algorithm gets lower. So in order to improve the precision of recommendation system, this paper considered user-trust network and user rating bias had influence on the accuracy of recommendation system, designed a probabilistic matrix factorization which integrates user-trust network and user rating bias. According to the results, the proposed algorithm is superior to probabilistic matrix factorization, and has a better prediction.

Copyright

© 2017, 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  - Qi He
AU  - Yan-fen Cheng
PY  - 2017/01
DA  - 2017/01
TI  - Algorithm optimization of recommendation based on probabilistic matrix factorization
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 1361
EP  - 1366
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-16.2016.306
DO  - 10.2991/icmmita-16.2016.306
ID  - He2017/01
ER  -