Assessing new correlation-based collaborative filtering approaches for binary market basket data

作者：

Highlights：

• We investigate the problems of Pearson correlation-based approaches.

• To resolve the problems, we develop two new correlation-based approaches.

• The new approaches outperform the existing methods.

摘要

•We investigate the problems of Pearson correlation-based approaches.•To resolve the problems, we develop two new correlation-based approaches.•The new approaches outperform the existing methods.

论文关键词：Binary market basket data,Collaborative filtering,Pearson correlation,Top-N accuracy

论文评审过程：Received 10 February 2018, Revised 4 March 2018, Accepted 4 March 2018, Available online 10 March 2018, Version of Record 16 March 2018.

论文官网地址：https://doi.org/10.1016/j.elerap.2018.03.002