Analisis Pola Perjalanan Penumpang LRT di Palembang Menggunakan Metode K-Means Clustering Berdasarkan Data Gate dan Waktu Perjalanan
DOI:
https://doi.org/10.55606/jutiti.v6i2.7380Keywords:
K-Means Clustering, Knowledge Discovery in Databases, Palembang LRT, Passenger Segmentation, Travel Pattern.Abstract
This study analyzes travel patterns of Single Trip ticket users of the Light Rail Transit (LRT) in Palembang City using the K-Means Clustering method within the Knowledge Discovery in Databases (KDD) framework. The dataset comprises 9,377 Single Trip ticket transaction records from the BPKARSS ticketing system on August 6, 2025. Modeled attributes include origin station code (gate-in), destination station code (gate-out), departure time in decimal format, and estimated travel duration derived through feature engineering. The Elbow Method identified K=3 as the selected cluster count based on the inflection point of the WCSS curve, further supported by a Silhouette Score of 0.3044 (moderate category), indicating discernible but partially overlapping clusters. K-Means with K-Means++ initialization produced three passenger segments: Cluster 0: Short-Distance Travel Pattern (39.8%; n=3,735), Cluster 1: Medium-Distance Travel Pattern (29.0%; n=2,724), and Cluster 2: Long-Distance Travel Pattern (31.1%; n=2,918). The results indicate that all cluster centroids fall within the midday period (12:45–13:45 WIB), which differs from conventional peak-hour assumptions. These findings offer an empirical basis for consideration in operational policy formulation.
Downloads
References
Arief Rahman Ramadhan, & Anita Diana. (2025). Penerapan algoritma K-means untuk klasterisasi jumlah penumpang angkutan umum di Jakarta. Infotek: Jurnal Informatika dan Teknologi, 8(1), 228–238. https://doi.org/10.29408/jit.v8i1.28195
Chen, A. H. L., Liang, Y. C., Chang, W. J., Siauw, H. Y., & Minanda, V. (2022). RFM model and K-means clustering analysis of transit traveller profiles: A case study. Journal of Advanced Transportation, 2022, 1108105. https://doi.org/10.1155/2022/1108105
Gustriansyah, R., Puspasari, S., Sanmorino, A., & Suhandi, N. (2025). Forecasting light rail transit passenger demand using parameter-tuned exponential smoothing models. Journal of Information Engineering and Educational Technology, 9(2), 101–112. https://doi.org/10.26740/jieet.v9n2.p101-112
Hagi, M., Suroyo, H., Wijaya, A., & Syazili, A. (2023). Data analysis automatic fare collection Light Rail Transit Jakarta using the cluster method. Journal of Computer Science, Information Technology and Telecommunication Engineering, 4(2), 465–473. https://doi.org/10.30596/jcositte.v4i2.16413
Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann.
Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Morgan Kaufmann.
Jain, A. K. (2010). Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8), 651–666. https://doi.org/10.1016/j.patrec.2009.09.011
Jain, A. K. (2010). Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8), 651–666. https://doi.org/10.1016/j.patrec.2009.09.011
Jamilah, W., & Amanah, T. (2024). Performance analysis of public transport feeder Light Rapid Transit (LRT) Palembang South Sumatra. Atlantis Press International BV. https://doi.org/10.2991/978-94-6463-386-3_24
Khairunnisa, H. R., & Hendrawan, A. (2025). LSTM forecasting and K-means clustering for passenger mobility management at bus terminals. Journal of Information Systems and Informatics, 7(3), 2129–2146. https://doi.org/10.51519/journalisi.v7i3.1159
Llatas, C., Soust-Verdaguer, B., Torres, L. C., & Cagigas, D. (2024). Application of knowledge discovery in databases (KDD) to environmental, economic, and social indicators used in BIM workflow to support sustainable design. Journal of Building Engineering, 91, 109546. https://doi.org/10.1016/j.jobe.2024.109546
MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1, 281–297.
MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1, 281–297.
Qin, Y., Guo, J., Xu, P., Wang, L., & Xia, B. (2025). Passenger flow-oriented operating period division in urban rail transit: A hybrid SOM and K-means clustering approach. Symmetry, 17(11), 11860. https://doi.org/10.3390/sym17111860
Saputra, A., & Yusuf, R. (2024). Perbandingan algoritma DBSCAN dan K-means dalam segmentasi pelanggan pengguna transportasi publik Transjakarta menggunakan metode RFM. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 4(4), 1346–1361. https://journal.irpi.or.id/index.php/malcom/article/view/1516
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jurnal Teknik Informatika dan Teknologi Informasi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
