Utilization of machine learning to detect the possibility of suspicious financial transactions
Keywords:
KNIME; Machine learning; Detect suspicious transactions; Financial transactions; Supervised learning algorithmAbstract
In order to prevent money laundering and terrorism financing, it is critical for banks to develop an effective mechanism to detect suspicious transactions. Nowadays, one of the most widely developed methods is machine learning. This article aims to discuss the best algorithm model in machine learning to detect possibilities for Suspicious Financial Transactions in XYZ Bank. The machine learning method used is supervised machine learning, with three models compared: Decision Tree, Gradient Boosting, and Random Forest. The tool used is The Konstanz Information Miner (KNIME). According to the findings of the study, the best model for detecting the possibility of SFT in bank XYZ is random forest with an accuracy rate of 99,98%. Based on this level of accuracy, this study reveals that a machine learning approach using historical company data makes a significant contribution to XYZ bank in detecting Suspicious Financial Transactions.
References
Ayunita, Y., Yahanan, A., & Syaifuddin, M. (2019). Perlindungan Hukum Terhadap Pengemudi Taksi
(Mitra) Berbasis Online Pada PT. Grab Indonesia. Lex Lata, 1(1).
Hossain, S., Sarma, D., Tuj-Johora, F., Bushra, J., Sen, S., & Taher, M. (2019). A belief rule based
expert system to predict student performance under uncertainty. 2019 22nd International
Conference on Computer and Information Technology (ICCIT), 1–6.
Johnson, S. (2021). Top Risk Review November 2021. https://managingrisktogether.orx.org/
Krishnapriya, G., & Prabakaran, M. (2014). Money laundering analysis based on time variant
behavioral transaction patterns using data mining. Journal of Theoretical and Applied
Information Technology, 67(1), 12–17.
Kumar, A., Das, S., Tyagi, V., Shaw, R. N., & Ghosh, A. (2021). Analysis of classifier algorithms to
detect anti-money laundering. Computationally Intelligent Systems and Their Applications, 143–
Latif, A. (2020). Konsep Hukum Sumber Dana dari Nasabah Penyimpan pada Bank Buku I di
Indonesia dalam Menghindari Money Laundry. Repertorium: Jurnal Ilmiah Hukum
Kenotariatan, 9(1), 1–10.
Leo, M., Sharma, S., & Maddulety, K. (2019). Machine learning in banking risk management: A
literature review. Risks, 7(1), 29.
Medar, R., Rajpurohit, V. S., & Rashmi, B. (2017). Impact of training and testing data splits on
accuracy of time series forecasting in machine learning. 2017 International Conference on
Computing, Communication, Control and Automation (ICCUBEA), 1–6.
Panjaitan, H. T. (2022). Pengaruh Skeptisisme Profesional, Keahlian Forensik, Tekanan Waktu, Dan
Beban Kerja Terhadap Kemampuan Mendeteksi Kecurangan (Studi Pada Bpkp Perwakilan Provinsi Sumatera Utara). Universitas Atma Jaya Yogyakarta.
Priadana, M. S., & Sunarsi, D. (2021). Metode Penelitian Kuantitatif. Pascal Books.
Provost, F., & Fawcett, T. (2013). Data Science for Business: What you need to know about data
mining and data-analytic thinking. “ O’Reilly Media, Inc.”
Raiter, O. (2021). Applying supervised machine learning algorithms for fraud detection in anti-money
laundering. Journal of Modern Issues in Business Research, 1(1), 14–26.
Rong, G., Alu, S., Li, K., Su, Y., Zhang, J., Zhang, Y., & Li, T. (2020). Rainfall induced landslide
susceptibility mapping based on Bayesian optimized random forest and gradient boosting
decision tree models—A case study of Shuicheng County, China. Water, 12(11), 3066.
Vassallo, D., Vella, V., & Ellul, J. (2021). Application of gradient boosting algorithms for anti-money
laundering in cryptocurrencies. SN Computer Science, 2, 1–15.
Wicaksono, A. (2020). PPATK Sebut “Virtual Currency” Bisa Mendanai Terorisme.
www.cnnindonesia.com
