Analisis Perbandingan Metode K-Means dan Gaussian Mixture Model dalam Pengelompokan Playlist Musik Berbasis Fitur Audio

Daniel Prasetiyo Dodi Darmawan; Christopher Mathew Putra; Samuel Yahya; Darren Jusman; Alfi Syahrian; Vitri Tundjungsari

doi:10.55606/jitek.v6i1.10754

Authors

Daniel Prasetiyo Dodi Darmawan Universitas Esa Unggul
Christopher Mathew Putra Universitas Esa Unggul
Samuel Yahya Universitas Esa Unggul
Darren Jusman Universitas Esa Unggul
Alfi Syahrian Universitas Esa Unggul
Vitri Tundjungsari Universitas Esa Unggul

DOI:

https://doi.org/10.55606/jitek.v6i1.10754

Keywords:

Audio Features, Clustering, Music, Spotify, Unsupervised Learning

Abstract

Music streaming platforms rely on playlists as medium for users to store musical preferences and receive music recommendations based on the music stored. However, representing playlists as meaningful groups remains a major challenge due to the high diversity characteristics of music. In addition, the distribution of musical characteristics within playlists can vary significantly. This study aims to compare two clustering models with different approaches hard clustering using the K-Means method and soft clustering using the Gaussian Mixture Model (GMM). Playlists are represented as statistical aggregations of audio feature data from songs, such as energy, acousticness, and danceability. The hard clustering approach using K-Means produces compact and clearly separated clusters, while the Gaussian Mixture Model (GMM) generates clusters that capture playlist ambiguity, resulting in overlapping clusters due to its probabilistic nature. These differences have a direct impact on the implementation of the clustering results in downstream applications. This study emphasizes the importance of selecting an appropriate clustering method for further implementations, such as music recommendation systems, and provides insights into the trade-offs between interpretability and flexibility offered by both models.

References

[1] A. Ramadhanti, M. Nursaif, and A. M. I. Taufik, “Motivasi Penggunaan Spotify Sebagai Media Penyebarluasan Karya Musik Musisi Indie Lokal,” Pros. Ind. Res. Workshop Natl. Semin., vol. 10, no. 1, pp. 904–916, Aug. 2019, doi: 10.35313/irwns.v10i1.1489.

[2] R. Fasti and D. Avianto, “Implementasi Web Klasifikasi Suasana Hati Berdasarkan Potongan Lagu dengan Memanfaatkan Convolutional Neural Network,” J. Indones. Manaj. Inform. Dan Komun., vol. 5, no. 1, pp. 881–892, Jan. 2024, doi: 10.35870/jimik.v5i1.573.

[3] T.-H. Ito and H. Shiokawa, “An Effective Graph-based Music Recommendation Algorithm for Automatic Playlist Continuation,” in Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, in ASONAM ’23. New York, NY, USA: Association for Computing Machinery, Mar. 2024, pp. 459–463. doi: 10.1145/3625007.3627322.

[4] Spotify, "Web API Reference: Get Audio Features," Spotify for Developers, 2025. [Online]. Available: https://developer.spotify.com/documentation/web-api/reference/get-audio-features.

[5] P. R. Oktaviani, B. H. Iswanto, and H. Suhendar, “KARAKTERISTIK FITUR SUARA KETUKAN BUAH KELAPA BERDASARKAN DOMAIN WAKTU DAN DOMAIN FREKUENSI,” Jt. Pros. IPS Dan Semin. Nas. Fis., vol. 12, pp. 11–16, Jan. 2024, doi: 10.21009/03.1201.FA02.

[6] Y. Azzery, “ANALISIS STATISIK PERBANDINGAN MANIPULASI SUARA DAN SUARA ASLI MENGGUNAKAN TEKNIK AUDIO FORENSIK,” TEKNOKOM, vol. 3, no. 1, pp. 29–33, Apr. 2020, doi: 10.31943/teknokom.v3i1.50.

[7] M. L. M. Akhlak, N. Istifarani, R. Sulistiyo, and S. Anggraeni, “Perancangan Sistem Kunci Cerdas Berbasis IoT Dan RFID Dengan Fitur Audio Interaktif,” KETIK J. Inform., vol. 3, no. 02, pp. 51–62, Nov. 2025, doi: 10.70404/ketik.v3i02.316.

[8] F. Yuniardini and T. Widiyaningtyas, “Analisis Perbandingan Pearson Correlation dan Cosine Similarity pada Rekomendasi Musik berbasis Collaborative Filtering,” Edumatic J. Pendidik. Inform., vol. 8, no. 2, pp. 555–564, Dec. 2024, doi: 10.29408/edumatic.v8i2.27781.

[9] I. Yoshua and H. Bunyamin, “Pengimplementasian Sistem Rekomendasi Musik Dengan Metode Collaborative Filtering,” J. STRATEGI - J. Maranatha, vol. 3, no. 1, pp. 1–16, Apr. 2021, [Online]. Available: https://strategi.it.maranatha.edu/index.php/strategi/article/view/220.

[10] M. J. Yonathan, D. P. D. Darmawan, A. D. Rachmawanto, and A. Prabowo, “Sistem Rekomendasi Musik Berdasarkan Playlist dengan Collaborative Filtering,” J. Inform. Dan Tekonologi Komput. JITEK, vol. 5, no. 3, pp. 175–184, Nov. 2025, doi: 10.55606/jitek.v5i3.8039.

[11] R. Abrah, M. A. M. Hayat, and L. Lukman, “Penerapan Machine Learning untuk Mengklasifikasikan Genre Musik Berdasarkan Fitur Audio,” Arus J. Sains Dan Teknol., vol. 3, no. 2, pp. 204–211, Oct. 2025, doi: 10.57250/ajst.v3i2.1699.

[12] C. N. Silla, A. L. Koerich, and C. A. A. Kaestner, “A Machine Learning Approach to Automatic Music Genre Classification,” J. Braz. Comput. Soc., vol. 14, no. 3, pp. 7–18, Sep. 2008, doi: 10.1007/BF03192561.

[13] N. D. Marsya, M. M. Munadhil, M. A. Dzakyananta, K. Amaliah, and D. Rofianto, “Penerapan Algoritma Random Forest dalam Prediksi Emosi Musik Berdasarkan Karakteristik Fitur Audio Spotify,” J. Sains Inform. Terap., vol. 4, no. 2, pp. 435–440, Aug. 2025, doi: 10.62357/jsit.v4i2.648.

[14] R. I. Safitri and S. Ningsih, “KLASTERISASI LAGU PADA PLATFORM SPOTIFY BERDASARKAN FITUR AUDIO MENGGUNAKAN ALGORITMA K-MEANS DAN K-MEANS++,” J. Sist. Inf. Bisnis JUNSIBI, vol. 6, no. 2, pp. 247–257, Oct. 2025, doi: 10.55122/junsibi.v6i2.1684.

[15] M. D. Rumpumbo and I. M. W. Wirawan, “Optimasi Model Gaussian Mixture Model (GMM) untuk Klasifikasi Genre Musik Berbasis Mel-Frequency Cepstral Coefficients (MFCC),” J. Nas. Teknol. Inf. Dan Apl., vol. 4, no. 1, pp. 153–160, Nov. 2025, doi: 10.24843/JNATIA.2025.v04.i01.p17.

[16] V. Tundjungsari, Dasar Machine Learning (Edisi Revisi). Sleman, Yogyakarta: Deepublish, 2024.

[17] Y. Zhang et al., “Gaussian Mixture Model Clustering with Incomplete Data,” ACM Trans Multimed. Comput Commun Appl, vol. 17, no. 1s, p. 6:1-6:14, Mar. 2021, doi: 10.1145/3408318.

[18] C.-W. Chen, P. Lamere, M. Schedl, and H. Zamani, “Recsys challenge 2018: automatic music playlist continuation,” in Proceedings of the 12th ACM Conference on Recommender Systems, in RecSys ’18. New York, NY, USA: Association for Computing Machinery, Sep. 2018, pp. 527–528. doi: 10.1145/3240323.3240342.

[19] M. Riani, A. C. Atkinson, and A. Corbellini, “Automatic robust Box–Cox and extended Yeo–Johnson transformations in regression,” Stat. Methods Appl., vol. 32, no. 1, pp. 75–102, Mar. 2023, doi: 10.1007/s10260-022-00640-7.

[20] N. A. Yolandari, L. E. Butarbutar, G. C. H. Rajagukguk, M. F. Zulfi, Arnita, and F. Ramadhani, “ANALISIS PERBANDINGAN K-MEANS DAN DBSCAN DALAM PENGELOMPOKAN DATA TRAVEL REVIEW RATINGS MENGGUNAKAN EVALUASI SILHOUETTE INDEX DAN DAVIES-BOULDIN INDEX,” J. Inform. Dan Tek. Elektro Terap., vol. 13, no. 3, Jul. 2025, doi: 10.23960/jitet.v13i3.6884.

[21] T. O. Kvålseth, “Coefficient of variation: the second-order alternative,” J. Appl. Stat., vol. 44, no. 3, pp. 402–415, Feb. 2017, doi: 10.1080/02664763.2016.1174195.