Service Recommendation Method Based on Collaborative Filtering and Random Forest

DOI

10.2991/mcei-15.2015.5How to use a DOI?

Keywords

Services Recommended; Collaborative Filtering; Cross Validation Model; Random Forest Model; Multiply Users

Abstract

With the development and popularization of E-commerce, more and more information services have appeared on the web. In order to meet users requirements more accurate, several service recommendation systems had been set up. Many methods have been proposed to discover users' interest for service recommendation, such as collaborative filtering and content based service recommendation. In this paper, a new service recommendation method is proposed based on user's interest, which combines collaborative filtering based on multiply users and random forest based on single user, and this fusion method uses cross validation model. This method can improve cold start and pick up speed .Experiment results show that the method can discover users' interest efficiently and is more accurate. This method can combine two basic methods so that the result is more accurate.

Copyright

© 2015, 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  - Lijing Xing
AU  - Delong Ma
AU  - Bingxian Ma
PY  - 2015/06
DA  - 2015/06
TI  - Service Recommendation Method Based on Collaborative Filtering and Random Forest
BT  - Proceedings of the International Conference on Management, Computer and Education Informatization
PB  - Atlantis Press
SP  - 17
EP  - 21
SN  - 2352-538X
UR  - https://doi.org/10.2991/mcei-15.2015.5
DO  - 10.2991/mcei-15.2015.5
ID  - Xing2015/06
ER  -