Serendipity adjustable application recommendation via joint disentangled recurrent variational auto-encoder

作者：

Highlights：

• Mobile app recommender able to adjust the level of serendipity is proposed.

• It generates next app usage prediction based on the disentangled representation.

• We vary the attributes of the disentanglement for serendipitous recommender.

• It shows better results than other benchmark methods in the experiments.

摘要

•Mobile app recommender able to adjust the level of serendipity is proposed.•It generates next app usage prediction based on the disentangled representation.•We vary the attributes of the disentanglement for serendipitous recommender.•It shows better results than other benchmark methods in the experiments.

论文关键词：Application recommendation,Serendipity,Disentangled representation,Variational auto-encoder,Application prediction

论文评审过程：Received 14 June 2019, Revised 21 September 2020, Accepted 6 October 2020, Available online 9 October 2020, Version of Record 13 November 2020.

论文官网地址：https://doi.org/10.1016/j.elerap.2020.101017