Scalable recommendations using decomposition techniques based on Voronoi diagrams
作者：
Highlights：
• A decomposition based recommendation approach is proposed.
• Voronoi diagram is used to partition the users’ space of the system.
• User partitions are treated independently to generate scalable recommendations.
• Spatial autocorrelation index values are used to justify the decomposition.
• Improved the recommendation quality for the boundary users of a Voronoi cell.
摘要
•A decomposition based recommendation approach is proposed.•Voronoi diagram is used to partition the users’ space of the system.•User partitions are treated independently to generate scalable recommendations.•Spatial autocorrelation index values are used to justify the decomposition.•Improved the recommendation quality for the boundary users of a Voronoi cell.
论文关键词：Voronoi diagrams,Collaborative filtering,Recommendation algorithm,Scalability
论文评审过程：Received 2 May 2020, Revised 21 December 2020, Accepted 26 February 2021, Available online 19 March 2021, Version of Record 19 March 2021.
论文官网地址：https://doi.org/10.1016/j.ipm.2021.102566
