SpotiPred: A Machine Learning Approach Prediction of Spotify Music Popularity by Audio Features
Joshua S. Gulmatico, Julie Ann B. Susa, Mon Arjay F. Malbog, Aimee G. Acoba, Marte D. Nipas, Jennalyn N. Mindoro
Abstract
Music consumption patterns could alter due to digitization, and music popularity was redefined in the streaming era. The number of people using Spotify is constantly growing. It has risen to become one of the most popular internet music providers in recent years. People have been listening to my favorite performers and receiving new song recommendations via the Spotify app for the past year. The research looks at the relationship between song data – audio attributes from the Spotify database (for example, key and tempo) – and song popularity, as measured by the number of Spotify streams a song has. To develop a high accuracy model for predicting hit songs, the researcher investigates four machine learning algorithms (MLAs): Linear Regression, Random Forest Classifier, and K-means Clustering. This study presents a prediction model for determining whether a piece of music is popular in the mainstream and using machine learning to classify songs based on their popularity.