Fraud Detection Using Machine Learning in Banking Operations
2025 Innovations in Intelligent Systems and Applications Conference, ASYU 2025, Bursa, Türkiye, 10 - 12 Eylül 2025, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/asyu67174.2025.11208285
- Basıldığı Şehir: Bursa
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: Anomaly Detection, Financial Transactions, Fraud Detection, LightGBM, Local Outlier Factor (LOF), SMOTE
- Maltepe Üniversitesi Adresli: Evet
Özet
This study aims to develop an effective fraud detection system for financial transactions by proposing a hybrid approach that combines the Local Outlier Factor (LOF) algorithm with the gradient boosting method LightGBM. To address the common challenge of data imbalance in fraud detection, the Synthetic Minority Over-sampling Technique (SMOTE) is applied. The model's performance is rigorously evaluated on the PaySim dataset, focusing on key metrics such as accuracy, precision, recall, and F1-score. The results demonstrate that this hybrid approach provides an efficient and reliable solution for identifying fraudulent activities in simulated banking transaction data.