Predicting Song Popularity Using Data Analysis

Title

Predicting Song Popularity Using Data Analysis

Creator

Medows K.J.; Leisha R.; Thiruthuvanathan M.M.

Description

In today's music landscape, predicting a song's success is crucial for musicians, record labels, and streaming platforms. This paper introduces a methodology for estimating popularity using Spotify data, termed the 'Proxy Popularity Score.' Three models - Random Forest, LightGBM Regressor, and XGBoost Regressor - are utilized for prediction. Performance metrics including mean absolute error, mean squared error, root mean squared error, and R-squared error are employed to evaluate model accuracy. Correlation values of 99.85%, 99.87%, and 99.84% are achieved for XGBoost, LightGBM, and Random Forest respectively. The study concludes with a ranking of songs based on predicted popularity scores. 2024 IEEE.

Source

Proceedings of InC4 2024 - 2024 IEEE International Conference on Contemporary Computing and Communications

Date

2024-01-01

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

LightGBM Regressor; Mean Absolute Error; Mean Squared Error; Popularity prediction; R-squared; Random Forest Regressor; Root Mean Squared Error; Spotify; XGBoost Regressor

Coverage

Medows K.J., CHRIST (Deemed To Be University), Computer Science and Engineering, Bangalore, India; Leisha R., CHRIST (Deemed To Be University), Computer Science and Engineering, Bangalore, India; Thiruthuvanathan M.M., CHRIST (Deemed To Be University), Computer Science and Engineering, Bangalore, India

Rights

Restricted Access

Relation

ISBN: 979-835038365-2

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/InC460750.2024.10649267

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85203798493&doi=10.1109%2fInC460750.2024.10649267&partnerID=40&md5=c2a733a0dd2a82747b74ae41f294636b