An Improved Collaborative Filtering Algorithm Based on Multi-Context Awareness
- 10.2991/iccmcee-15.2015.28How to use a DOI?
- Context-Aware; Collaborative Filtering; Recommender Systems
In the research field of recommender systems, people tend to focus on mining relationship between users and items, but less take the additional contextual information into consideration. To solve the problem, we put forward an improved collaborative filtering algorithm based on multiple contexts (MCCF). The algorithm utilizes AHP to calculate the weight vector of context features, then transform contextual information into SimHash sequence based on the weight vector to calculate context similarity. Use the composite similarity which compounds the user preference and the context to structure the target user’s nearest neighbor set. Finally, integrate the composite similarity into the traditional collaborative filtering algorithm to predict preferences and recommend items. Experiments show that MCCF is superior to the traditional ones and single context ones in both performance and recommendation accuracy.
- © 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/).
Cite this article
TY - CONF AU - Yuan Bai AU - Yu Fang PY - 2015/11 DA - 2015/11 TI - An Improved Collaborative Filtering Algorithm Based on Multi-Context Awareness BT - Proceedings of the 2015 4th International Conference on Computer, Mechatronics, Control and Electronic Engineering PB - Atlantis Press SP - 141 EP - 149 SN - 2352-5401 UR - https://doi.org/10.2991/iccmcee-15.2015.28 DO - 10.2991/iccmcee-15.2015.28 ID - Bai2015/11 ER -