Analisis Pola Fraud pada Payment Gateway Berbasis Unsupervised Learning Menggunakan Isolation Forest
Keywords:
Fraud Detection; Payment Gateway; Isolation ForestAbstract
Perkembangan teknologi digital yang pesat telah mendorong peningkatan transaksi online melalui Payment Gateway. Namun, hal ini juga diiringi dengan meningkatnya kasus penipuan (Fraud) yang merugikan merchant dan konsumen. Penelitian ini bertujuan untuk mengembangkan sistem deteksi Fraud pada Payment Gateway menggunakan metode Unsupervised Learning dengan algoritma Isolation Forest. Dataset yang digunakan merupakan dataset transaksi kartu kredit yang diperoleh dari Kaggle, yang terdiri dari 284.807 transaksi dengan komposisi 0,17% Fraud. Selain itu, untuk keperluan validasi, digunakan juga data sandbox dari Midtrans sebanyak 500 transaksi. Model Isolation Forest dilatih dengan pendekatan data balancing dan hyperparameter tuning. Hasil pengujian menunjukkan bahwa model mencapai akurasi sebesar 43,81%, precision 27,83%, dan recall 78,32%. Meskipun precision masih rendah, recall yang tinggi mengindikasikan bahwa model mampu mendeteksi sebagian besar transaksi Fraud. Sistem diimplementasikan dalam bentuk aplikasi web berbasis Laravel yang terintegrasi dengan Flask API untuk deteksi Fraud secara real-time, serta dilengkapi dengan dashboard admin untuk monitoring transaksi dan status Fraud. Penelitian ini memberikan kontribusi berupa sistem deteksi Fraud yang dapat membantu merchant dalam mengidentifikasi transaksi mencurigakan secara otomatis, serta menjadi dasar pengembangan sistem keamanan yang lebih baik di masa depan.
References
Ali, A., Abd Razak, S., Othman, S. H., Eisa, T. A. E., Al-Dhaqm, A., Nasser, M., Elhassan, T., Elshafie, H., & Saif, A. (2022). Financial Fraud Detection Based on Machine Learning: A Systematic Literature Review. In Applied Sciences (Switzerland) (Vol. 12, Number 19). MDPI. https://doi.org/10.3390/app12199637
Al-Khowarizmi, A., Syah, R., & Elveny, M. (2022). The model of business intelligence development by applying cooperative society based financial technology. In X. S. Yang, S. Sherratt, N. Dey, & A. Joshi (Eds.), Proceedings of Sixth International Congress on Information and Communication Technology (Vol. 235, pp. 117–125). Springer. https://doi.org/10.1007/978-981-16-2377-6_13
Apruzzese, G., Laskov, P., Montes De Oca, E., Mallouli, W., Brdalo Rapa, L., Grammatopoulos, A. V., & Di Franco, F. (2023). The Role of Machine Learning in Cybersecurity. Digital Threats: Research and Practice, 4(1). https://doi.org/10.1145/3545574
Ardhi Baskara, A., Maharani Piranti, N., Fahrury Romdendine Manajemen Teknologi Keimigrasian, M., Imigrasi Jalan Raya Gandul No, P., & Depok, K. (2025). FRAMEWORK DATA MINING : SEBUAH SURVEI. In Jurnal Mahasiswa Teknik Informatika) (Vol. 9, Number 3).
Bank Indonesia. (2024, January 17). BI catat nilai transaksi digital banking 2023 Rp 58.478,24 triliun. PPID Provinsi Kalimantan Timur. https://ppid-dev.kaltimprov.go.id/post/bi-catat-nilai-transaksi-digital-banking-2023-rp-58-478-24-triliun
BCBS. (2023). Basel Committee on Banking Supervision Discussion paper Digital Fraud and banking: supervisory and financial stability implications. www.bis.org
Bodepudi, H. (2021). Credit Card Fraud Detection Using Unsupervised Machine Learning Algorithms. International Journal of Computer Trends and Technology, 69(8), 1–3. https://doi.org/10.14445/22312803/IJCTT-V69I8P101
Diva, M., & Anshori, I. (2024). Penggunaan E-Wallet Sebagai Inovasi Transaksi Digital: Literatur Review. 2(6). https://journal.institercom-edu.org/index.php/multiple
FutureCISO. (2025). Rising scam threats in Indonesia’s real-time payments ecosystem. https://futureciso.tech/rising-scam-threats-in-indonesias-real-time-payments-ecosystem/
George, M. Z. H., Alam, M. K., & Hasan, M. T. (2023). MACHINE LEARNING FOR FRAUD DETECTION IN DIGITAL BANKING: A SYSTEMATIC LITERATURE REVIEW. ASRC Procedia: Global Perspectives in Science and Scholarship, 03(01), 37–61. https://doi.org/10.63125/913ksy63
Harlan, H. (2026). Sinergi : Jurnal Ilmiah Multidisiplin Penipuan dalam Ekosistem Digital Finance: Kajian Teoritis dan Strategi Mitigasi di Indonesia. Jurnal Ilmiah Multidisiplin. https://publikasi.ahlalkamal.com/index.php/sinergi
Hasyim, Pulungan, F. A., Sitorus, H. N. S., & Muliana, R. S. (2023). Increasing the Use of Electronic Money Transactions (E-Money) in Indonesian Society. Indonesian Journal of Accounting and Financial Technology, 1(2), 59–70. https://doi.org/10.55927/crypto.v1i2.4267
Karczmarek, P., Kiersztyn, A., Pedrycz, W., & Al-Enezi, J. R. (2021). Generalized Isolation Forest for anomaly Detection. Applied Soft Computing, 107, Article 107354. https://doi.org/10.1016/j.asoc.2021.107354
Kennedy, K., Mac Namee, B., & Delany, S. J. (2022). A novel approach for Unsupervised Learning of highly-imbalanced data. In Proceedings of the 2022 IEEE 5th International Conference on Cognitive Machine Intelligence (CogMI) (pp. 10–18). https://doi.org/10.1109/CogMI56440.2022.00018
Lesouple, J., Baudoin, C., Spigai, M., & Tourneret, J.-Y. (2021). Pattern Recognition Letters Generalized Isolation Forest for Anomaly Detection. https://www.sciencedirect.com/science/article/pii/S0167865521002063
Nursansiwi, D. A., & Armiani, A. (2022). Peran Strategi Bisnis Fintech Payment Gateway dalam Meningkatkan Kinerja UMKM di NTB. Owner, 7(1), 367–378. https://doi.org/10.33395/owner.v7i1.1219
Parmar, P. P., & Sheth, K. P. (n.d.). Peer-Reviewed, Multidisciplinary & Multilingual Journal DIGITAL FINANCIAL TRANSACTION USAGE AND DEMOGRAPHICS OF CUSTOMERS: EVIDENCE FROM GUJARAT. Retrieved http://vidyajournal.org
Prasad, K. A., Pattabirani, G., & Sundaramoorthy, K. (2025). Insights into Anomaly Detection: A Survey and Comparative Analysis of Techniques for Time Series Data from Industrial Environment (pp. 871–907). https://doi.org/10.2991/978-94-6463-662-8_71
Pratiwi, A. A., Aulia, N., Nikmah, N., Indriani, D., Audy, K., Studi, P., & Syariah, E. (2026). Perkembangan dan Implementasi Digital Payment dalam Mendukung Sistem Pembayaran Cashless di Indonesia. Jurnal Ekonomi Manajemen Dan Bisnis, 3, 343–352. https://doi.org/10.62017/jemb
Puspitasari, A. (2025). Transformation of the Financial Sector and Digital Payments in Indonesia. ORGANIZE: Journal of Economics, Management and Finance, 4(2), 145–154. https://doi.org/10.58355/organize.v4i2.122
Shaveta. (2023). A review on machine learning. International Journal of Science and Research Archive, 9(1), 281–285. https://doi.org/10.30574/ijsra.2023.9.1.0410
Siahaan, R. A., Sianturi, R. A., & Korespondensi, P. (2024). ANALISIS PERBANDINGAN PAYMENT GATEWAY UNTUK SISTEM PEMBAYARAN BERBASIS APLIKASI DENGAN COMPARATIVE STUDY. 11(2), 291–296. https://doi.org/10.25126/jtiik.2024117680
Thar, K. W., & Wai, T. T. (2024). Machine learning based predictive modelling for Fraud Detection in digital banking. In Proceedings of the 2024 IEEE Conference on Computer Applications (ICCA) (pp. 1–5). https://doi.org/10.1109/ICCA62361.2024.10532788
Zanah, A. S., Calista, B., Dewi, W. N., & Sokibi, P. (2025). Deteksi Dini Fraud pada Layanan Keuangan Digital Menggunakan Metode Random Forest. In Indonesian Journal on Data Science (Vol. 3, Number 2). https://ejournal.unjaya.ac.id/index.php/ijds
