About this document
Arxiv:2006.03715V1 (Cs - Ir) 5 Jun 2020 by nguyenmaitrang105 is a document available to read on EtoBox.
This paper presents a two-sided post-processing approach using the Deferred Acceptance algorithm to optimize the balance between accuracy and diversity in recommendation systems. The proposed method aims to increase aggregate diversity while minimizing the loss in recommendation accuracy for end users, addressing the trade-off between user and item utilities. Empirical results demonstrate the effectiveness of this approach in enhancing both aggregate diversity and item-side utility across various recommenda
- Author
- nguyenmaitrang105
- Language
- EN