Detecting Suspicious Foreign Currency Transactions Using SOM and K-Means++ Algorithm
DOI:
https://doi.org/10.30812/corisindo.v1.5571Keywords:
Clustering, deteksi transaksi, K-Means++, Self-Organizing Map, uang kertas asingAbstract
Dalam konteks perekonomian global yang terus berkembang dan kompleks, aktivitas jual beli uang kertas asing melibatkan volume transaksi yang besar dan beragam, sehingga meningkatkan risiko terjadinya transaksi keuangan mencurigakan. Berbagai penelitian sebelumnya telah memanfaatkan metode klasifikasi dan clustering, namun sebagian masih terbatas pada satu algoritma sehingga kurang optimal dalam mendeteksi pola anomali secara akurat. Penelitian ini bertujuan untuk mengembangkan sistem deteksi transaksi mencurigakan menggunakan kombinasi algoritma Self-Organizing Map (SOM) dan K-Means++ agar dapat mengidentifikasi pola transaksi abnormal secara cepat dan akurat. Data transaksi periode 2021–2022 digunakan sebagai data latih, kemudian dianalisis melalui tahapan praproses, normalisasi, pelatihan model, dan evaluasi menggunakan confusion matrix untuk menghitung akurasi, presisi, recall, spesifisitas, dan F1-score. Hasil pengujian menunjukkan bahwa model mampu mendeteksi transaksi mencurigakan dengan tingkat akurasi 95,45% pada data latih dan 77,75% pada data uji, dengan recall tinggi yang menandakan sensitivitas deteksi terhadap transaksi fraud. Temuan ini menegaskan bahwa metode SOM dan K-Means++ efektif sebagai alat bantu identifikasi transaksi mencurigakan, sekaligus menyediakan landasan untuk pengembangan sistem deteksi otomatis yang lebih adaptif pada sektor keuangan.
References
[1] Y. Safitri and D. Z. Putri, ‘Analisis Determinan Cadangan Devisa di Indonesia’, Jurnal Kajian Ekonomi dan Pembangunan, vol. 3, no. 4, pp. 97–108, 2021, [Online]. Available: http://ejournal.unp.ac.id/students/index.php/epb/index
[2] Bank Indonesia, Peraturan Bank Indonesia Nomor 18/20/PBI/2016 Tahun 2016 tentang Kegiatan Usaha Penukaran Valuta Asing Bukan Bank. Indonesia: LN 2016/NO 194; PERATURAN.GO.ID : 30 HLM, 2016. Accessed: Sep. 20, 2024. [Online]. Available: https://peraturan.bpk.go.id/Details/135678/peraturan-bi-no-1820pbi2016-tahun-2016
[3] Y. Aditia, Financial Integrity Rating on Money Laundering and Terrorist Financing. Jakarta: Pusat Pelaporan dan Analisis Transaksi Keuangan (PPATK), 2021.
[4] S. M. Darwish, A. I. Salama, and A. A. Elzoghabi, ‘Intelligent Approach to Detecting Online Fraudulent Trading with Solution for Imbalanced Data in Fintech Forensics’, Sci Rep, vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-01223-8.
[5] A. Vaid, C. Reddy, and S. Prabhagaran, ‘A Hybrid Framework for Dynamic Clustering and Anomaly Detection in SAP ERP Systems’, International Journal of Computer Science and Mobile Computing, vol. 13, no. 12, pp. 23–34, Dec. 2024, doi: 10.47760/ijcsmc . 2024.v13i12.003.
[6] Y. Chen, C. Zhao, Y. Xu, C. Nie, and Y. Zhang, ‘Year-over-Year Developments in Financial Fraud Detection via Deep Learning: A Systematic Literature Review’, Journal of Financial Data Science, vol. 7, no. 2, pp. 45–59, Jul. 2025, [Online]. Available: http://arxiv.org/abs/2502.00201
[7] W. N. Dilla and R. L. Raschke, ‘Data visualization for fraud detection: Practice implications and a call for future research’, International Journal of Accounting Information Systems, vol. 16, pp. 1–22, Mar. 2015, doi: 10.1016/j.accinf.2015.01.001.
[8] S. Bagga, A. Goyal, N. Gupta, and A. Goyal, ‘Credit Card Fraud Detection using Pipeling and Ensemble Learning’, in Procedia Computer Science, Elsevier B.V., 2020, pp. 104–112. doi: 10.1016/j.procs.2020.06.014.
[9] D. Olszewski, ‘Fraud Detection Using Self-Organizing Map Visualizing the User Profiles’, Knowl Based Syst, vol. 70, pp. 324–334, Nov. 2014, doi: 10.1016/j.knosys.2014.07.008.
[10] Y. Y. Nguwi and S. Y. Cho, ‘An Unsupervised Self-Organizing Learning with Support Vector Ranking for Imbalanced Datasets’, Expert Syst Appl, vol. 37, no. 12, pp. 8303–8312, 2010, doi: 10.1016/j.eswa.2010.05.054.
[11] I. Nunes et al., Artificial Neural Networks: A Practical Course. Switzerland: Springer International, 2017. doi: 10.1007/978-3-319-43162-8.
[12] D. Arthur and S. Vassilvitskii, ‘K-Means++: The Advantages of Careful Seeding’, in Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), New Orleans, Louisiana: Society for Industrial and Applied Mathematics (SIAM), Jan. 2007, pp. 1027–1035.
[13] N. B. N. Nyakundi, S. M. Reynolds, and H. Reza, ‘Scenario-Based Approach to Systematically Derive Test Cases for Systems’, in 2023 IEEE International Conference on Electro Information Technology (eIT), IEEE, May 2023, pp. 51–58. doi: 10.1109/eIT57321.2023.10187246.
[14] O. Rainio, J. Teuho, and R. Klén, ‘Evaluation Metrics and Statistical Tests for Machine Learning’, Sci Rep, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-56706-x.
[15] F. Bankole and Z. Vara, ‘Artificial Intelligence System for Value Added Tax Collection via Self Organizing Map (SOM)’, J Forensic Sci & Criminal Inves, vol. 18, no. 2, 2024, doi: 10.19080/JFSCI.2024.18.555981.
[16] A. Nowak-Brzezinska and C. Horyn, ‘Self-Organizing Map Algorithm as a Tool for Outlier Detection’, in Procedia Computer Science, Elsevier B.V., 2022, pp. 6162–6171. doi: 10.1016/j.procs.2022.09.276.
[17] S. Ruiz-Moreno, A. Núñez-Reyes, A. García-Cantalapiedra, and F. Pavón, ‘Prototype Generation Method using a Growing Self-Organizing Map Applied to the Banking Sector’, Neural Comput Appl, vol. 35, no. 24, pp. 17579–17597, Aug. 2023, doi: 10.1007/s00521-023-08630-w.
[18] G. Douzas, R. Rauch, and F. Bacao, ‘G-SOMO: An Oversampling Approach Based on Self-Organized Maps and Geometric SMOTE’, Expert Syst Appl, vol. 183, Nov. 2021, doi: 10.1016/j.eswa.2021.115230.
[19] L. Concetti, G. Mazzuto, F. E. Ciarapica, and M. Bevilacqua, ‘An Unsupervised Anomaly Detection Based on Self-Organizing Map for the Oil and Gas Sector’, Applied Sciences (Switzerland), vol. 13, no. 6, Mar. 2023, doi: 10.3390/app13063725.
[20] Y. Wang, ‘A Data Balancing and Ensemble Learning Approach for Credit Card Fraud Detection’, in 2025 4th International Symposium on Computer Applications and Information Technology (ISCAIT), New York: IEEE, Mar. 2025, pp. 386–390. doi: https://doi.org/10.48550/arXiv.2503.21160.
