Digitalni čuvar finansija: Uloga veštačke inteligencije (AI) u bankarstvu i otkrivanju prevara
Ključne reči:
veštačka inteligencija, AI, bankarstvo, finansijske prevare, detekcija prevara, upravljanje rizicimaApstrakt
Brzi rast digitalnih transakcija i sve veća složenost finansijskih prevara povećali su potrebu za naprednim mehanizmima za njihovo otkrivanje i sprečavanje u savremenom bankarstvu. Veštačka inteligencija (VI) postala je ključna transformativna tehnologija koja menja tradicionalne sisteme kontrole, revizije i upravljanja rizicima, omogućavajući obradu velikih i kompleksnih skupova podataka u realnom vremenu. Ovaj rad ispituje ulogu VI u bankarskom sektoru, sa posebnim fokusom na njenu primenu u detekciji i prevenciji prevara. Analiziraju se najčešće korišćene tehnike VI — modeli mašinskog učenja, sistemi za detekciju anomalija i prediktivna analitika — i ocenjuje se njihov doprinos unapređenju tačnosti, brzine i efikasnosti procesa upravljanja rizicima. Rad takođe razmatra integraciju VI u bankarske operacije, ističući praktične koristi, ali i izazove primene, uključujući transparentnost algoritama, kvalitet podataka, sajber‑bezbednosne rizike, regulatornu usklađenost i rastuću zavisnost od automatizovanih sistema podrške odlučivanju. Nalazi pokazuju da VI značajno poboljšava sposobnost finansijskih institucija da rano identifikuju sumnjive aktivnosti, smanjujući potencijalne gubitke i jačajući otpornost sistema. Ipak, njen puni potencijal može se ostvariti samo kroz uravnotežen pristup koji kombinuje tehnološke inovacije, adekvatan regulatorni nadzor i kontinuirani ljudski nadzor.
Reference
Association of Certified Fraud Examiners. (2026). 2026 anti-fraud technology benchmarking report. https://www.acfe.com/fraud-resources/anti-fraud-technology-benchmarking-report
Bank for International Settlements. (2024). Central banks must prepare for AI's profound impact on the economy and financial system. https://www.bis.org/press/p240625.htm
Bank for International Settlements. (2025). Project symbiosis: AI and big data technologies for supply chain sustainability disclosure. https://www.bis.org/about/bisih/topics/cbdc/symbiosis.htm
Chilukala, R. (2025). AI-driven fraud detection models in cloud-based banking ecosystems: A comprehensive analysis. European Journal of Computer Science and Information Technology, 13(48), 45-55.
European Banking Authority, & European Central Bank. (2024). EBA and ECB release joint report on payment fraud data. https://www.eba.europa.eu/publications-and-media/press-releases/eba-and-ecb-release-joint-report-payment-fraud
European Central Bank, & European Banking Authority. (2024). Report on payment fraud data in the European Economic Area. https://www.ecb.europa.eu/press/pr/date/2024/html/ecb.pr240801~f21cc4a009.en.html
Financial Stability Board. (2025). Annual report. https://www.fsb.org/work-of-the-fsb/financial-innovation-and-structural-change/
Gentyala, R. (2023). From rules to probabilities: A comparative analysis of anomaly detection logic in AI-driven versus rule-based banking compliance systems. European Journal of Advances in Engineering and Technology, 10(12), 134–150.
Husnaningtyas, N., & Dewayanto, T. (2023). Financial fraud detection and machine learning algorithm (unsupervised learning): Systematic literature review. Jurnal Riset Akuntansi dan Bisnis Airlangga (JRABA), 8(2).
Johora, F. T., Hasan, R., Farabi, S. F., Alam, M. Z., Sarkar, I., & Al Mahmud, A. (2024, June). AI advances: Enhancing banking security with fraud detection. In 2024 First International Conference on Technological Innovations and Advance Computing (TIACOMP) (pp. 289–294). IEEE.
Narender, M., & Anand, A. J. (2025). Artificial intelligence in financial fraud detection. In Handbook of AI-driven threat detection and prevention (pp. 193–207). CRC Press.
Onyshchenko, O., Ternovska, V., & Kovalov, V. (2025). Artificial intelligence in banking: Modern models and implementation challenges. Social Development: Economic and Legal Issues, (12).
Sharma, P. (2024). Transforming banking through artificial intelligence: Enhancing service, efficiency, and security for the digital age. International Journal of Science and Technology (IJST), 1(4), 10–21.
Usmani, U. A., Happonen, A., & Watada, J. (2022, July). A review of unsupervised machine learning frameworks for anomaly detection in industrial applications. In Science and Information Conference (pp. 158–189). Springer International Publishing.
Zainal, A. (2023). Role of artificial intelligence and big data technologies in enhancing anomaly detection and fraud prevention in digital banking systems. International Journal of Advanced Cybersecurity Systems, Technologies, and Applications, 7(12), 1–10.
