Timeliness in recommender systems
作者：
Highlights：
• Recommendation accuracy is much lower in temporal than random data division.
• We introduce a metric measuring the timeliness of the recommendation.
• Low accuracy is caused by the tendency of algorithms to recommend out-of-date items.
• Timeliness factor is used to modify the recommendation score of items.
• The recommendation accuracy is largely improved with the timeliness-based approach.
摘要
•Recommendation accuracy is much lower in temporal than random data division.•We introduce a metric measuring the timeliness of the recommendation.•Low accuracy is caused by the tendency of algorithms to recommend out-of-date items.•Timeliness factor is used to modify the recommendation score of items.•The recommendation accuracy is largely improved with the timeliness-based approach.
论文关键词：Recommender systems,Bipartite networks,Timeliness,Data division
论文评审过程：Received 8 January 2017, Revised 26 March 2017, Accepted 15 May 2017, Available online 19 May 2017, Version of Record 23 May 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.05.038
