Research Article
Innovative Tunes: Utilizing Machine Learning for Predicting Spotify Music Popularity Based on Audio Features
@INPROCEEDINGS{10.1007/978-3-031-77075-3_23, author={Shubham Joshi and Neha Gupta and Rupali Mahajan}, title={Innovative Tunes: Utilizing Machine Learning for Predicting Spotify Music Popularity Based on Audio Features}, proceedings={Cognitive Computing and Cyber Physical Systems. 5th EAI International Conference, IC4S 2024, Bhimavaram, India, April 5--7, 2024, Proceedings, Part-I}, proceedings_a={IC4S}, year={2025}, month={2}, keywords={Digitization of music consumption Music popularity Spotify Machine learning algorithms Linear Regression Music streaming}, doi={10.1007/978-3-031-77075-3_23} }- Shubham Joshi
Neha Gupta
Rupali Mahajan
Year: 2025
Innovative Tunes: Utilizing Machine Learning for Predicting Spotify Music Popularity Based on Audio Features
IC4S
Springer
DOI: 10.1007/978-3-031-77075-3_23
Abstract
The digitalization of music has brought significant changes to popular music in the age of streaming media. As the number of users of a platform like Spotify continues to grow, it has become one of the most important online music providers today.. People rely on the Spotify app to listen to their favorite artists and discover new music. This study aims to investigate the relationship between music data, specifically audio features (such as key and tempo) extracted from the Spotify database, and popular music (measured by the number of streams a song receives on the Spotify platform). The main goal is to create an accurate and reliable model that can accurately predict whether a song will become a hit or not. To achieve this goal, researchers looked at four different machine learning algorithms: linear regression, random forest classifiers, and K-means clustering. These algorithms are used to analyze data and find patterns that help predict popular songs accurately. Finally, the research proposed a predictive model that uses machine learning techniques to determine the importance of music. Using these standards, songs can be classified according to their needs, thus providing a better perspective on artists, music producers, and the music industry as a whole. It is hoped that this research will help to better understand the factors that influence the success of the song and pave the way for greater decision-making in music.
