SpotHitPy: A Study For ML-Based Song Hit Prediction Using Spotify

• DOI: 10.48550/arxiv.2301.07978
• Publication Date: 2023-01-01
• Authors: Ioannis Dimolitsas; Spyridon Kantarelis; Afroditi Fouka
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Sound (cs.SD); Audio and Speech Processing (eess.AS); 0202 electrical engineering, electronic engineering, information engineering; FOS: Electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Computer Science - Sound; Electrical Engineering and Systems Science - Audio and Speech Processing; Machine Learning (cs.LG)

In this study, we approached the Hit Song Prediction problem, which aims to predict songs will become Billboard hits. We gathered a dataset of nearly 18500 hit and non-hit extracted their audio features using Spotify Web API. test four machine-learning models on our dataset. were able success song with approximately 86\% accuracy. The most succesful algorithms Random Forest Support Vector Machine.