Fraud Detection in Monetary Transactions

• Published in: 2024 Second International Conference on Advances in Information Technology (ICAIT) Vol. 1; pp. 1 - 6
• Main Authors: Nair, Rekha R, Vjeya Kaveri, V., Sivakumar, Shrinidhi, Janani R, Srinithi, Babu, Tina, Sharma R, Rajesh
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24-07-2024
• Subjects: Accuracy; Bagged trees classifier; Banking; Credit cards; Fraud detection; Machine learning; Machine learning algorithms; Monetary transactions; Prediction algorithms; Predictive models; Random Forest Classifier; Training
• DOI: 10.1109/ICAIT61638.2024.10690586

Fraudulent transactions pose significant challenges to the banking industry, leading to significant losses. Conventional identification methods often struggle to keep up with changing fraud techniques. In this study, proposed a new approach using a hybrid algorithm combining Bagged Trees Classifier and Random Forest. Bagged Trees Classifier classifies instances by tree struc- ture, while Random Forest aggregates predictions from multiple trees to increase accuracy in detecting fraudulent behavior the proposed approach aims to overcome existing limitations role by reducing false positives and improving detection accuracy. out line the method for data set partitioning, model selection, training, and evaluation, and demonstrate the effectiveness of our approach. By combining a bagged trees classifier with a random forest, the proposed approach provides a robust framework for detecting fraudulent transactions in banking, providing proactive anti-fraud strategies while reducing financial losses.