Predicting Afrobeats Hit Songs Using Spotify Data

TL;DR

This paper explores predicting popular Afrobeats songs on Spotify using machine learning, achieving high accuracy with Random Forest and Gradient Boosting algorithms on a dataset of over 2000 songs.

Contribution

It introduces a new approach to Hit Song Science specifically for Afrobeats using Spotify data and demonstrates effective predictive models.

Findings

Random Forest and Gradient Boosting achieved around 86% F1 score.

The dataset of 2063 songs was successfully used for prediction.

Machine learning models can effectively predict hit songs in the Afrobeats genre.

Abstract

This study approached the Hit Song Science problem with the aim of predicting which songs in the Afrobeats genre will become popular among Spotify listeners. A dataset of 2063 songs was generated through the Spotify Web API, with the provided audio features. Random Forest and Gradient Boosting algorithms proved to be successful with approximately F1 scores of 86%.