Bayesian Personalized Ranking with Multi-Channel User Feedback
Bayesian Personalized Ranking with Multi-Channel User Feedback
B. Loni,Roberto Pagano,M. Larson,A. Hanjalic
2016 · DOI: 10.1145/2959100.2959163
ACM Conference on Recommender Systems · 161 Citations
TLDR
Multi-feedback Bayesian Personalized Ranking (MF-BPR), a pairwise method that exploits different types of feedback with an extended sampling method that equates feedback sources with "levels" that reflect the expected contribution of the signal, is proposed.