Collaborative Filtering on Skewed Datasets

摘要：

Many real life datasets have skewed distributions of events when the probability of observing few events far exceeds the others. This paper, we observed that in skewed datasets the state of the art collaborative filtering methods perform worse than a simple probabilistic model. Our test bench includes a real ad click stream dataset which is naturally skewed. The same conclusion obtained even from the popular movie rating dataset when we pose a binary prediction problem of whether a user will give maximum rating to a movie or not.

关键词： Collaborative filtering skewed dataset pLSA.

作者: Somnath Banerjee Krishnan Ramanathan

作者单位: Hewlett-Packard Labs Bangalore, India

会议类型: 国际会议

会议名称: 第十七届国际万维网大会(the 17th International World Wide Web Conference)(WWW08)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-04-21（万方平台首次上网日期，不代表论文的发表时间）