Learning content similarity for music recommendation

TL;DR

This paper introduces a method to optimize content-based music similarity by learning from collaborative filter data, enabling accurate recommendations for new or unpopular songs.

Contribution

It presents a novel approach that enhances content-based similarity metrics using collaborative filter data, improving recommendation accuracy for unseen or rare items.

Findings

Significant accuracy improvements over existing content-based methods

Effective recommendations for novel and unpopular songs

Efficient representations of audio content

Abstract

Many tasks in music information retrieval, such as recommendation, and playlist generation for online radio, fall naturally into the query-by-example setting, wherein a user queries the system by providing a song, and the system responds with a list of relevant or similar song recommendations. Such applications ultimately depend on the notion of similarity between items to produce high-quality results. Current state-of-the-art systems employ collaborative filter methods to represent musical items, effectively comparing items in terms of their constituent users. While collaborative filter techniques perform well when historical data is available for each item, their reliance on historical data impedes performance on novel or unpopular items. To combat this problem, practitioners rely on content-based similarity, which naturally extends to novel items, but is typically out-performed by collaborative filter methods. In this article, we propose a method for optimizing contentbased similarity by learning from a sample of collaborative filter data. The optimized content-based similarity metric can then be applied to answer queries on novel and unpopular items, while still maintaining high recommendation accuracy. The proposed system yields accurate and efficient representations of audio content, and experimental results show significant improvements in accuracy over competing content-based recommendation techniques.