A vertex similarity index for better personalized recommendation

TL;DR

This paper introduces CosRA, a new vertex similarity index that enhances personalized recommendation accuracy, diversity, and novelty without requiring parameter tuning, outperforming existing methods on real datasets.

Contribution

The paper proposes the CosRA index, combining cosine similarity and resource-allocation, and demonstrates its superior performance in real recommender systems.

Findings

CosRA outperforms benchmark methods in accuracy, diversity, and novelty.

CosRA is parameter-free, simplifying real-world application.

Adding parameters does not significantly improve CosRA's performance.

Abstract

Recommender systems benefit us in tackling the problem of information overload by predicting our potential choices among diverse niche objects. So far, a variety of personalized recommendation algorithms have been proposed and most of them are based on similarities, such as collaborative filtering and mass diffusion. Here, we propose a novel vertex similarity index named CosRA, which combines advantages of both the cosine index and the resource-allocation (RA) index. By applying the CosRA index to real recommender systems including MovieLens, Netflix and RYM, we show that the CosRA-based method has better performance in accuracy, diversity and novelty than some benchmark methods. Moreover, the CosRA index is free of parameters, which is a significant advantage in real applications. Further experiments show that the introduction of two turnable parameters cannot remarkably improve the overall performance of the CosRA index.