Serendipitous Personalized Ranking for Top-N Recommendation
Qiuxia Lu, Tianqi Chen, Weinan Zhang, Diyi Yang, Yong Hai Yu · 2012
Abstract—Serendipitous recommendation has benefitted both e-retailers and users. It tends to suggest items which are both unexpected and useful to users. These items are not only profitable to the retailers but also surprisingly suitable to consumers ’ tastes. However, due to the imbalance in observed data for popular and tail items, existing collaborative filtering methods fail to give satisfactory serendipitous recommen-dations. To solve this problem, we propose a simple and effective method, called serendipitous personalized ranking. The experimental results demonstrate that our method sig-nificantly improves both accuracy and serendipity for top-N recommendation compared to traditional personalized ranking methods in various settings.