探探项目 - 提升推荐系统的多样性

---

概述

实现了论文[1]中提出了5种Re-Rank排序方法，得出结论： Absolute likeability排序方法效果最好。

推荐系统的准确度和多样度的测量方法由论文[2]提供

详细文档可以参见:

diversity survey

diversity experiment

Reference

[1] Adomavicius, G., & Kwon, Y. (2009, December). Toward more diverse recommendations: Item re-ranking methods for recommender systems. In Workshop on Information Technologies and Systems.

[2] Cheng, P., Wang, S., Ma, J., Sun, J., & Xiong, H. (2017, April). Learning to Recommend Accurate and Diverse Items. In Proceedings of the 26th International Conference on World Wide Web (pp. 183-192). International World Wide Web Conferences Steering Committee.