arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01522math.NAcs.IRcs.LGcs.NAstat.AP
收藏

通过模拟用户兴趣提高推荐相关性

Improving Recommendation Relevance by simulating User Interest

Salesforce(赛富时)

Alexander Kushkuley, Joshua Correa

摘要:

大多数(如果不是所有的话)在线项目到项目推荐系统依赖于项目之间相似性的距离(排名)的估计。对于在线推荐系统,这种相似性度量的时间敏感性是非常重要的。我们观察到,建议“新近”可以直接和透明地保持迭代减少排名的非活动项目。本文简要总结了算法的发展基于这一自我解释的观察。这项工作背后的基本思想是在线推荐系统的专利。

英文摘要:

Most if not all on-line item-to-item recommendation systems rely on estimation of a distance like measure (rank) of similarity between items. For on-line recommendation systems, time sensitivity of this similarity measure is extremely important. We observe that recommendation "recency" can be straightforwardly and transparently maintained by iterative reduction of ranks of inactive items. The paper briefly summarizes algorithmic developments based on this self-explanatory observation. The basic idea behind this work is patented in a context of online recommendation systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑