METODE SCORING AGREGASI PERILAKU AKUN UNTUK KLASIFIKASI RISIKO PADA DATASET E-WALLET PAYSIM
DOI:
https://doi.org/10.32699/biner.v5i2.11414Keywords:
Agregasi Perilaku, Dataset PaySim, Aplikasi E-Wallet M-Pesa, Rule-Based Scoring, Scoring Tingkat Risiko.Abstract
Penelitian tentang deteksi penipuan transaksi e-wallet berbasis machine learning menghasilkan klasifikasi biner pertransaksi tanpa profil risiko akun yang komprehensif, sehingga terdapat kesenjangan dalam penilaian tingkat risiko per akun pada dataset PaySim. Penelitian ini bertujuan mengembangkan metode Account Behavior Aggregation Scoring (ABAS) untuk mengklasifikasikan tingkat risiko akun e-wallet secara transparan dan terukur tanpa memerlukan model pembelajaran mesin. Metode ABAS menghitung skor S menggunakan formula S = min(S₁+S₂+S₃+S₄+D, 100) dari lima komponen. Validasi dilakukan pada 6.362.620 transaksi dataset PaySim (CC0, Kaggle) melalui tiga kelompok eksperimen: K-1 (isolasi pengaruh S₁ dengan variasi frekuensi), K-2 (isolasi pengaruh S₂ dengan variasi jumlah), dan K-3 (validasi data nyata terhadap ground truth isFraud). Hasil menunjukkan 6.353.307 akun unik berhasil di-score dengan rata-rata skor 20,21. Komponen S₄ mendominasi kontribusi dataset nyata sebesar 38,9%, diikuti S₁ (32,4%) dan S₂ (18,9%). Distribusi kategori menunjukkan 2.228 akun (0,04%) berkategori TINGGI dengan fraud rate 0,6%, tertinggi di antara semua kategori. Tren kenaikan monoton fraud rate dari 0,0% (SANGAT RENDAH) hingga 0,6% (TINGGI) memvalidasi sifat diskriminatif klasifikasi. Dataset berlabel terbuka yang dihasilkan memungkinkan penerapan pemantauan berbasis risiko sesuai kerangka CDD FATF tanpa membangun model penilaian dari awal.
Downloads
References
[1] E. A. Lopez-Rojas, A. Elmir, and S. Axelsson, “Paysim: A financial mobile money simulator for fraud detection,” 28th European Modeling and Simulation Symposium, EMSS 2016, no. c, pp. 249–255, 2016.
[2] A. Ali et al., “Financial Fraud Detection Based on Machine Learning: A Systematic Literature Review,” Applied Sciences (Switzerland), vol. 12, no. 19, 2022, doi: 10.3390/app12199637.
[3] L. Hernandez Aros, L. X. Bustamante Molano, F. Gutierrez-Portela, J. J. Moreno Hernandez, and M. S. Rodríguez Barrero, “Financial fraud detection through the application of machine learning techniques: a literature review,” Humanit. Soc. Sci. Commun., vol. 11, no. 1, pp. 1–22, 2024, doi: 10.1057/s41599-024-03606-0.
[4] P. Hajek, M. Z. Abedin, and U. Sivarajah, “Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework,” Information Systems Frontiers, vol. 25, no. 5, pp. 1985–2003, 2023, doi: 10.1007/s10796-022-10346-6.
[5] E. A. L. M. Btoush, X. Zhou, R. Gururajan, K. C. Chan, R. Genrich, and P. Sankaran, “A systematic review of literature on credit card cyber fraud detection using machine and deep learning,” PeerJ Comput. Sci., vol. 9, pp. 1–66, 2023, doi: 10.7717/PEERJ-CS.1278.
[6] M. E. Lokanan, “Predicting mobile money transaction fraud using machine learning algorithms,” no. April, pp. 1–15, 2023, doi: 10.1002/ail2.85.
[7] P. Alumona, O. Lawal, M. O. Ikhifa, D. O. Agbeso, and O. Awele, “Fraud Detection in Financial Transactions Using Machine Learning : Insights from the PaySim Mobile Money Dataset,” 2025.
[8] I. Sadgali, N. Sael, and F. Benabbou, “Human behavior scoring in credit card fraud detection,” IAES International Journal of Artificial Intelligence, vol. 10, no. 3, pp. 698–706, 2021, doi: 10.11591/IJAI.V10.I3.PP698-706.
[9] S. Metha, “AI-Driven Fraud Detection: A Risk Scoring Model for Enhanced Security in Banking,” Journal of Engineering Research and Reports, vol. 27, no. 3, pp. 23–34, 2025, doi: 10.9734/jerr/2025/v27i31415.
[10] A. Mutemi and F. Bacao, “E-Commerce Fraud Detection Based on Machine Learning Techniques: Systematic Literature Review,” Big Data Mining and Analytics, vol. 7, no. 2, pp. 419–444, 2024, doi: 10.26599/BDMA.2023.9020023.
[11] C. Wang, “The behavioral sign of account theft: Realizing online payment fraud alert,” IJCAI International Joint Conference on Artificial Intelligence, vol. 2021-Janua, pp. 4611–4618, 2020, doi: 10.24963/ijcai.2020/636.
[12] Cut Dinda Rizki Amirillah, “Detecting Fraudulent Transaction in Banking Sector Using Rule-Based Model and Machine Learning,” Jurnal Nasional Teknik Elektro dan Teknologi Informasi, vol. 14, no. 2, pp. 96–102, 2025, doi: 10.22146/jnteti.v14i2.17410.
[13] D. Vijayanand and G. S. Smrithy, “Explainable AI - enhanced ensemble learning for financial fraud detection in mobile money transactions,” 2025, doi: 10.1177/18724981241289751.
[14] I. Mulyana, M. B. Ulum, I. Engineering, U. Esa, and U. Jakarta, “APPLICATION OF MACHINE LEARNING MODELS FOR FRAUD,” vol. 10, no. 4, pp. 759–769, 2025, doi: 10.33480/jitk.v10i4.6420.APPLICATION.
[15] L. Thomas, J. Crook, and D. Edelman, Credit Scoring and Its Applications, Second Edition. in Mathematics in Industry. Society for Industrial and Applied Mathematics, 2017.
[16] G. F. O. R. A. R. Approach, “THE BANKING SECTOR,” no. October, 2014.
[17] H. Liu, F. Hussain, C. L. I. M. Tan, and M. Dash, “Discretization : An Enabling Technique,” pp. 393–423, 2002.
[18] R. Mouawi, I. H. Elhajj, A. Chehab, and A. Kayssi, “Crowdsourcing for click fraud detection,” EURASIP J. Inf. Secur., vol. 2019, no. 1, pp. 1–18, 2019, doi: 10.1186/s13635-019-0095-1.
[19] A. Patil, S. Mahajan, J. Menpara, S. Wagle, P. Pareek, and K. Kotecha, “Enhancing fraud detection in banking by integration of graph databases with machine learning,” MethodsX, vol. 12, no. April, 2024, doi: 10.1016/j.mex.2024.102683.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Biner : Jurnal Ilmiah Informatika dan Komputer
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
An author who publishes in this Journal agrees to the following terms:
- Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal
- Author is able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book) with the acknowledgement of its initial publication in this journal.
- Author is permitted and encouraged to post his/her work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of the published work (See The Effect of Open Access).
