A polynomial modeling based algorithm in top-N recommendation

作者：

Highlights：

• Recommender HDMR, a polynomial based algorithm for top-N recommendation is proposed.

• The proposed method is applied to an industrial data set from apparels domain.

• The data organization is based on collaborative filtering approach.

• The modelling part includes the implementation of the HDMR philosophy.

• The results show that Recommender HDMR works better than state-of-the-art methods.

摘要

•Recommender HDMR, a polynomial based algorithm for top-N recommendation is proposed.•The proposed method is applied to an industrial data set from apparels domain.•The data organization is based on collaborative filtering approach.•The modelling part includes the implementation of the HDMR philosophy.•The results show that Recommender HDMR works better than state-of-the-art methods.

论文关键词：Recommender systems,Purchase history matrix,HDMR,E-commerce

论文评审过程：Received 7 August 2016, Revised 1 March 2017, Accepted 2 March 2017, Available online 3 March 2017, Version of Record 11 March 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.03.005