KREDIT KARTALARI BILAN BOG'LIQ FIRIBGARLIKNI ANIQLASHDA XGBOOST VA NEYRON TARMOQLARNI QIYOSIY TAHLILI

Authors

  • Tursunov Bobur Ortiqmirzayevich O'zbekiston Respublikasi Bank-moliya akademiyasi professori Author
  • To'xtamishev Rahimjon Azamat o'g'li O'zbekiston Respublikasi Bank-moliya akademiyasi, 70410601 - Bank ishi yo'nalishi magistratura tinglovchisi Author

Keywords:

Keywords: Kalit so'zlar: XGBoost, neyron tarmoqlar, LSTM, kredit karta firibgarligi, mashinali o'qitish, anomaliyalarni aniqlash, kiberxavfsizlik.

Abstract

Zamonaviy bank tizimida kredit kartalari orqali amalga oshiriladigan tranzaksiyalar hajmining ortib borishi firibgarlik holatlarining ham sonini, ham murakkabligini oshirmoqda. Ushbu tezisda kredit karta firibgarligini aniqlashda gradient busting algoritmi XGBoost hamda chuqur neyron tarmoqlar (Multilayer Perceptron va LSTM arxitekturalari) samaradorligi qiyosiy tahlil qilinadi. Tahlil natijalariga ko'ra, kichik va o'rta hajmdagi, keskin nomutanosib ma'lumotlar to'plamlarida XGBoost tezroq o'qitiladi va yuqori aniqlik ta'minlaydi, neyron tarmoqlar esa tranzaksiyalar ketma-ketligidagi vaqtinchalik bog'liqliklarni yaxshiroq o'zlashtiradi. Ikkala yondashuvni birlashtiruvchi gibrid modellar amaliyotda eng yuqori samaradorlikni ta'minlashi aniqlangan.

References

1.Dal Pozzolo A., Boracchi G., Caelen O., Alippi C., Bontempi G. Credit card fraud detection: a realistic modeling and a novel learning strategy // IEEE Transactions on Neural Networks and Learning Systems. — 2018. — Vol. 29, No. 8. — P. 3784–3797.

2.Jurgovsky J., Granitzer M., Ziegler K., Calabretto S., Portier P.-E., He-Guelton L., Caelen O. Sequence classification for credit-card fraud detection // Expert Systems with Applications. — 2018. — Vol. 100. — P. 234–245.

3.Randhawa K., Loo C.K., Seera M., Lim C.P., Nandi A.K. Credit card fraud detection using AdaBoost and majority voting // IEEE Access. — 2018. — Vol. 6. — P. 14277–14284.

4.4 Shi J. Credit Card Fraud Detection Based on ANN and XGBoost // Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence (ECAI). — SciTePress, 2024. — Vol. 1. — P. 195–199. DOI: 10.5220/0013212700004568.

5.5 Andrade-Arenas L., Yactayo-Arias C. Comparative Analysis of Machine Learning Models for Credit Card Fraud Detection Using SMOTE for Class Imbalance // International Journal of Safety and Security Engineering. — 2025. — Vol. 15, No. 5. — P. 893–901. DOI: 10.18280/ijsse.150504.

6.6 Saucedo R., Inga P., Escobedo Cardenas E.J. Enhancing Credit Card Fraud Detection with Clickstream-Based Behavioral Features // IEEE Conference Proceedings. — 2025.

7.7 Anitha P., Sowmiya N., Mathiyalagan P., Padmapriya V., Sekharreddy B., Bala M. Real-Time Credit Card Fraud Detection Using Optimized XGBoost with Intelligent Pattern Adaptation // Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT'25). — SciTePress, 2025. — Vol. 1. — P. 608–614. DOI: 10.5220/0013870200004919.

Downloads

Published

2026-09-22