İŞLETME İÇİ SUİİSTİMALİN TESPİTİNDE MAKİNE ÖĞRENMESİNİN ROLÜ

Yıl 2024, Cilt: 6 Sayı: 2, 151 - 172, 19.05.2025

Teoman Samet Temuçin

Öz

Kurumları tehdit eden önemli operasyonel risklerden biri de iç suiistimaldir. Söz konusu eylemleri önleyici proaktif kontrollerin varlığı kadar, hızlı bir şekilde tespit edilmesini sağlayacak reaktif sürekli izleme mekanizmalarının mevcudiyeti de önem arz etmektedir. İlk çalışmamızın (Temuçin et al., 2021) devamı niteliğinde olan bu makalemizde, Türkiye’nin önemli bankalarından biri olan Garanti BBVA’nın iç suiistimal tespitinde büyük veri dönüşüm hikayesini bir adım daha ileriye taşıyoruz. “Kural-bazlı” olarak nitelendirilen ve başarısını kanıtlamış mevcut tespit yaklaşımına, biriken veri havuzu sayesinde makine öğrenmesinin nasıl entegre edildiğinden bahsedeceğiz. Makine öğrenmesiyle desteklenen yeni hibrid modelle; daha etkin bir sürekli izleme yaklaşımı kurulduğu gibi, yüksek iç suiistimal tespit oranı ve düşük Banka kaybı gibi kritik göstergelerde de yıllara sari sürdürülebilirlik kazanmak mümkün olmuştur. İç suiistimalin tespitinde başarısını kanıtlayan ve makine öğrenmesinin entegre edildiği güncel metodolojimizin sektöre de ilham kaynağı olmasını umuyoruz.

Anahtar Kelimeler

İç suiistimal , Büyük veri , Makine öğrenmesi , XGBoost

ROLE OF MACHINE LEARNING IN INTERNAL FRAUD DETECTION

Öz

One of the operational risks faced by the entities is internal fraud. In addition to preventive proactive controls, the existence of reactive continuous risk monitoring to quickly detect them is of great importance. In this paper written as the continuation of our first study (Temuçin et al., 2021), we take one step further the big data transformation story of Garanti BBVA - one of the most important banks of Türkiye - regarding detection of internal frauds. We will explain how machine learning was integrated into the “rule-based” approach with proven success thanks to the accumulated data pool. The hybrid model supported with machine learning has established a more effective continuous monitoring approach and also ensured the maintenance of sustainable critical metrics such as high internal fraud detection ratio and low Bank loss. We hope that our current methodology with proven success in detection of internal frauds and with its recent integration with machine learning will be an inspiration for the sector.

Anahtar Kelimeler

Internal fraud , Big data , Machine learning , XGBoost

Kaynakça

• Albashrawi, M. (2016). Detecting Financial Fraud Using Data Mining Techniques: A Decade Review from 2004 to 2015, Journal of Data Science, 14(3), 553-570.
• Association of Certified Fraud Examiners (ACFE) (2024). Occupational Fraud 2024: A Report to the Nations. Retrieved from https://legacy.acfe.com/report-to-the-nations/2024/
• Association of Certified Fraud Examiners (ACFE) (2020). Global Study on Occupational Fraud and Abuse: Report to the Nations. Retrieved from https://legacy.acfe.com/report-to-the-nations/2020/
• Babuşcu, S., Hazar, A., & Iskender, A. (2018). Banka Risk Yönetimi: Basel I - II - III - IV Düzenlemeleri. Bankacılık Akademisi Yayınları.
• Baesens, B., Vlasselaer, V., & Verbeke, W. (2015). Fraud Analytics Using Descriptive, Predictive, and Social Network Techniques: A Guide to Data Science for Fraud Detection. Wiley Publishing.
• Baesens, B., Höppner, S., & Verdonck, T. (2021). Data Engineering for Fraud Detection, Decision Support Systems, vol. 150, 113492.
• Becker, R., Volinsky, C., & Wilks, A. (2010). Fraud Detection in Telecommunications: History and Lessons Learned. Technometrics. 52(1), 20-33.
• Bolton, R. & Hand, D. (2002). Statistical Fraud Detection: A Review, Statistical Science. 17(3), 235-255. Cao, R., Liu, G., Xie, Y., & Jiang, C. (2021). Two-Level Attention Model of Representation Learning for Fraud Detection, IEEE Transactions on Computational Social Systems, 8(6), 1291-1301.
• Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge, Discovery and Data Mining, NY, USA, 785-794.
• Dhaliwal, S.S., Nahid, A.A., & Abbas, R. (2018). Effective Intrusion Detection System Using XGBoost. Information, 9(7), 149.
• Dhieb, N., Ghazzai, H., Besbes, H., & Massoud, Y. (2020) A Secure AI-Driven Architecture for Automated Insurance Systems: Fraud Detection and Risk Measurement, IEEE Access, vol. 8, 58546-58558.
• Fawcett, T. & Provost, F. (1997). Adaptive Fraud Detection, Data Mining and Knowledge Discovery, 1(3), 291-316.
• Friedman, J.H. (2001). Greedy Function Approximation: A Gradient Boosting Machine, The Annals of Statistics, 29(5), 1189-1232.
• Ge, D., Gu, J., Chang, S., & Cai, J. (2020). Credit Card Fraud Detection Using Lightgbm Model, 2020 International Conference on E-Commerce and Internet Technology, 232-236.
• Gomes, C., Jin, Z., & Yang, H. (2021). Insurance Fraud Detection with Unsupervised Deep Learning, Journal of Risk and Insurance, 88(3), 591-624.
• Ismail, M.M. & Haq, M.A. (2024). Enhancing Enterprise Financial Fraud Detection Using Machine Learning, Engineering, Technology & Applied Science Research, 14(4), 14854-14861.
• Khatri, S., Arora, A., & Agrawal, A. (2020). Supervised Machine Learning Algorithms for Credit Card Fraud Detection: A Comparison. 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence), IEEE, 680-683.
• Kolodiziev, O., Mints, A., Sidelov, P., Pleskun, I., & Lozynska, O. (2020). Automatic Machine Learning Algorithms for Fraud Detection in Digital Payment Systems. Eastern-European Journal of Enterprise Technologies, 5(107), 14-26.
• Li, S.H., Yen, D.C., Lu, W.H., & Wang C. (2012). Identifying the Signs of Fraudulent Accounts Using Data Mining Techniques. Computers in Human Behavior, 28(3), 1002-1013.
• Njoku, D., Iwuchukwu, V., Jibiri, J., Ikwuazom, C., Ofoegbu, C., & Nwokoma F. (2024). Machine Learning Approach for Fraud Detection System in Financial Institution: A Web Base Application. International Journal of Engineering Research and Development, 20(4), 1-12.
• Priscilla, C.V., & Prabha, D.P. (2020). Influence of Optimizing XGBoost to Handle Class Imbalance in Credit Card Fraud Detection, 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India, 1309-1315.
• Rosset, S., Murad, U., Neumann, E., Idan, Y, & Pinkas, G. (1999). Discovery of Fraud Rules for Telecommunications - Challenges and Solutions, In Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, NY: Association for Computing Machinery Press, 409-413.
• Shirgave, S. K., Awati, C. J., More, R., & Patil, S. S. (2019). A Review on Credit Card Fraud Detection Using Machine Learning, International Journal of Scientific and Technology Research, 8(10), 1217-1220.
• Sinap, V. (2024). Comparative Analysis of Machine Learning Techniques for Credit Card Fraud Detection: Dealing with Imbalanced Datasets. Turkish Journal of Engineering, 8(2), 196-208.
• Soviany, C. (2018). The Benefits of Using Artificial Intelligence in Payment Fraud Detection: A Case Study, Journal of Payments Strategy and Systems, 12(2), 102-110.
• Srivastava, N., & Salakhutdinov, R. (2014). Multimodal Learning with Deep Boltzmann Machines, Journal of Machine Learning Research, 15(84), 2949-2980.
• Temuçin, T. S., Erbaş, S., & Ay, A. (2021). Using Big Data in Internal Fraud Detection, TIDE AcademIA Research, 3(1), 55-82.
• Van Engelen, J.E., & Hoos, H.H. (2020). A Survey on Semi-supervised Learning, Machine Learning, 109, 373-440.
• Wei, Y., Qi, Y., Ma Q., Liu Z., Shen C., & Fang C. (2020). Fraud Detection by Machine Learning, 2nd International Conference on Machine Learning, Big Data and Business Intelligence, 101-115.