Comparative Analysis of Spotify Listener Behavior Between Free and Premium Users Using the K-Means Clustering Algorithm
Article Sidebar
Main Article Content
Abstract
The feature differences between Spotify Free and Premium services have the potential to shape different listening behavior patterns, while data-driven studies of user activity in Indonesia are still very limited. This study aims to analyze the listening behavior patterns of Spotify users based on subscription type using the K-Means clustering algorithm. The dataset used is the Spotify Global Streaming Data 2024, which includes quantitative variables such as average stream duration, skip rate, total streams, total hours streamed, and monthly listeners. The analysis begins with determining the optimal number of clusters using the Elbow method, followed by heatmap visualization and Principal Component Analysis (PCA) to identify behavioral characteristics within each cluster. The research results show three optimal clusters with significant differences between Free and Premium users. Free users have a higher average skip rate (28.7%) and shorter listening duration (3.4 minutes), while Premium users show a lower skip rate (16.2%) and longer listening duration (3.9 minutes). The silhouette score values of 0.57 for Free and 0.64 for Premium indicate good clustering quality. This finding confirms that the service model directly influences the intensity and consistency of digital music listening behavior. Implicatively, the results of this research can be used as a basis for developing content personalization strategies and improving user experience on online music platforms in the future.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1] D. Noviani, R. Pratiwi, S. Silvianadewi, M. B. Alexandri, and A. Hakim, “The Influence of Music Streaming on the Music Industry in Indonesia,” vol. 29, no. 1, 2020.
[2] I. Nilasari, R. Handayani, and D. Roespinuedji, “Do brand geographic location and price value stimulate intentions to premium services? Evidence from Spotify Indonesia,” vol. 11, no. 1, pp. 746–752, 2021, doi: 10.48047/rigeo.11.1.62.
[3] C. E. Hsu and B. Sandy, “Music Streaming Characteristics and Consumption Emotion as Determinants of Consumer Satisfaction and Purchase Intention,” vol. 17, no. 3, pp. 157–188, 2021, doi: 10.7903/cmr.20647.
[4] J. E. Alodia and A. R. Qastharin, “The Impact of Spotify Advertisements On Free Accounts To Purchase Decisions For Spotify Premium Accounts With Consumer Attitudes As The Mediating Variable,” vol. 2, no. 1, pp. 140–147, 2024, doi: 10.58229/jims.v2i1.171.
[5] M. D. Syafrudin and F. Ridhaningsih, “The Effect of Perceived Value and Customer Experience on Repurchase Intention of Premium Spotify Mediated by Satisfaction,” pp. 1349–1358, 2024.
[6] D. Holtz, B. Carterette, P. Chandar, Z. Nazari, and H. Cramer, “The Engagement-Diversity Connection: Evidence from a Field Experiment on Spotify,” pp. 1–58.
[7] N. Montecchio, P. Roy, and F. Pachet, “The skipping behavior of users of music streaming services and its relation to musical structure,” pp. 1–16, 2020, doi: 10.1371/journal.pone.0239418.
[8] M. S. Muryani and A. Muanas, “Spotify Premium Customer Loyalty: The Role of Perceived Value, Customer Experience, and Customer Satisfaction as Intervening Variables,” vol. 8, no. 3, pp. 194–208, 2025.
[9] M. R. Rosari, G. N. J. Adinegara, and N. P. D. Krismawintari, “The Influence of Perceived Benefit, Perceived Price, and Perceived Ease of Use on Purchase Decisions of Spotify Consumers (Case Study of Students Using the Spotify Application at Dhyana Pura University), ” vol. 3, no. 2, pp. 77–87, 2024.
[10] K. Bisma and C. Pramartha, “Segmentation of Spotify Users Based on Music Preferences Using the K-Means Clustering Algorithm,” vol. 3, no. November, pp. 37–42, 2024.
[11] A. P. Wicaksono and E. Andajani, “Factors Affecting Attitude towards Online Music Piracy and Willingness to Try Subscription-Based Music Services (SBMS)?” vol. 26, no. 1, pp. 37–49, 2023, doi: 10.14414/jebav.v26i1.2994.
[12] C. Pangestu and R. Wijaya, “X Spotify Cares Clustering Analysis using K-Means and K-Medoids,” vol. 8, pp. 497–507, 2024, doi: 10.30865/mib.v8i1.7279.
[13] M. I. Firmansyah, R. S. Rohman, and E. Marsusanti, “Application of the K-Means Clustering Algorithm to Attribute Features in Spotify Music Streaming Services,” vol. 2, no. 2, pp. 58–66, 2023.
[14] A. Anderson, L. Maystre, and I. Anderson, “Algorithmic Effects on the Diversity of Consumption on Spotify,” vol. 2, 2020.
[15] S. Shulhiyana and A. Voutama, “Application of the K-Means Clustering Method for Music Grouping Based on Audio Characteristics,” vol. 6, no. 2, 2025.
[16] J. Donier, “The universality of skipping behaviors on music streaming platforms,” no. iii, 2020.
[17] A. Ramadhinda, S. R. Manalu, and T. Pradekso “ The Influence of Perceptions of 'Spotify Wrapped' and Perceptions of Premium Benefits on Interest in Subscribing to Spotify Premium,”.
[18] R. Amanda, “Spotify WOM by Millennial Generation,” pp. 140–157, 2022.
[19] Nuryasin and A. T. Ferina, “Evaluation of Spotify Application Usability Using the System Usability Scale (SUS)
[20] S. E. Damayanti, M. I. Fajriana, D. Meilani, and S. S. Fatimah, “Exploring Insights into the Music Industry: Clustering the Most Popular Songs on Spotify 2024 Using the K-Means Clustering Method,” pp. 562–567, 2024.