A Recommendation Algorithm Uses Contribution Factor for Selecting Influential Neighbor

DOI

10.2991/ncce-18.2018.132How to use a DOI?

Keywords

KNN; contribution factor; neighbors; algorithm; recommendation performance.

Abstract

Collaborative filtering recommendation algorithm based on KNN neighbor selection does not consider the blind follower of neighbors when selecting neighbors, which causes some neighbor users to play a minor role in predicting the target user's scoring of unknown items. In response to this problem, a contribution factor is proposed. Jointly evaluate the item set from this perspective, consider the neighboring user's recommendation capability, calculate the neighboring user's recommendation contribution, combine the traditional user similarity to jointly select the neighbors, and recalculate the neighbor user's weight of the unknown project to improve the recommendation performance. Experimental results show that this improved algorithm improves recommendation accuracy.

Copyright

© 2018, 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  - Yuan Xie
AU  - Lei Ding
PY  - 2018/05
DA  - 2018/05
TI  - A Recommendation Algorithm Uses Contribution Factor for Selecting Influential Neighbor
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 800
EP  - 804
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.132
DO  - 10.2991/ncce-18.2018.132
ID  - Xie2018/05
ER  -