The Imbalanced Classification of Fraudulent Bank Transactions Using Machine Learning

Abstract

This article studies the development of a reliable AI model to detect fraudulent bank transactions, including money laundering, and illegal activities with goods and services. The proposed machine learning model uses the CreditCardFraud dataset and utilizes multiple algorithms with different parameters. The results are evaluated using Accuracy, Precision, Recall, F1 score, and IBA. We have increased the reliability of the imbalanced classification of fraudulent credit card transactions in comparison to the best known results by using the Tomek links resampling algorithm of the imbalanced CreditCardFraud dataset. The reliability of the results, using the proposed model based on the TPOT and RandomForest algorithms, has been confirmed by using 10-fold cross-validation. It is shown that on the dataset the accuracy of the proposed model detecting fraudulent bank transactions reaches 99.99%.