Mixtape Application: Music Map Methodology and Evaluation

TL;DR

This paper explores dimensionality reduction methods, Isomap and L-Isomap, to create a music map that visually represents song similarities for improved music recommendation systems.

Contribution

It compares two specific techniques for music mapping, providing insights into their effectiveness for song similarity visualization.

Findings

Isomap effectively captures global song relationships.

L-Isomap offers advantages in handling local structures.

Both methods improve music recommendation accuracy.

Abstract

This report discusses dimensionality reduction techniques used to create a music map - a map where the distances between songs represent their similarity and that can be used to recommend songs. We evaluate two techniques: Isomap and L-Isomap.