Music Recommendation on Spotify using Deep Learning

TL;DR

This paper explores deep learning techniques for music recommendation on Spotify, aiming to enhance user satisfaction by improving playlist personalization, achieving high training and validation accuracy.

Contribution

It introduces a deep learning architecture tailored for Spotify's music recommendation system, focusing on maximizing user likeability.

Findings

Achieved 98.57% training accuracy

Achieved 80% validation accuracy

Supports improved playlist personalization

Abstract

Hosting about 50 million songs and 4 billion playlists, there is an enormous amount of data generated at Spotify every single day - upwards of 600 gigabytes of data (harvard.edu). Since the algorithms that Spotify uses in recommendation systems is proprietary and confidential, code for big data analytics and recommendation can only be speculated. However, it is widely theorized that Spotify uses two main strategies to target users' playlists and personalized mixes that are infamous for their retention - exploration and exploitation (kaggle.com). This paper aims to appropriate filtering using the approach of deep learning for maximum user likeability. The architecture achieves 98.57% and 80% training and validation accuracy respectively.