Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Bulletin of Network Engineer and Informatics (BUFNETS)
Rismaria Sipayung
Universitas Mercu Buana Yogyakarta
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
SONG POPULARITY PREDICTION ON THE SPOTIFY PLATFORM USING MULTIPLE LINEAR REGRESSION WITH MIN-MAX NORMALIZATION Rismaria Sipayung; Mutaqin Akbar
Bulletin of Network Engineer and Informatics Vol. 4 No. 1 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) April 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/738832

Abstract

This study critically investigates whether three commonly used audio-level features of a song, duration, tempo, and energy, are by themselves, statistically capable of predicting song popularity on the Spotify platform. Using a multiple linear regression model estimated via Ordinary Least Squares (OLS) on 849 songs retrieved from Kaggle "Spotify Tracks Dataset", a publicly available collection spanning multiple genres and release periods, filtered to exclude duplicate records and songs with a popularity score of zero, we show that this is not the case. Prior to modeling, Min-Max normalization was applied to standardize variable scales. The model yields the equation Y = 42.4073 + (-5.2462)*X1 + (1.0306)*X2 + (-4.1247)*X3, but the overall F-test is not significant (F = 1.1789 < F-table = 2.6154, p = 0.3167), and none of the three predictors reach individual significance (all |t| < 1.53, p > 0.12). Pairwise correlations between each predictor and popularity are negligible (r = -0.037 for duration, r = -0.006 for tempo, r = -0.053 for energy), confirming that the linear structure captures essentially no signal in this dataset. We conclude that duration, tempo, and energy have effectively zero standalone predictive capability for Spotify popularity, and that normalization, while statistically inert with respect to R² and RMSE, remains necessary for producing comparable, interpretable coefficients. As a secondary, practical contribution, the analysis pipeline was deployed as an interactive web application (SpotiPredict, built with Python Flask) that exposes the full normalization and regression computation transparently to the user.
Co-Authors Mutaqin Akbar