Enhancing Credit Card Fraud Detection with Modified Binary Bat Algorithm: A Comparative Study with SVM, RF, and DT

Abstract

Numerous studies have revealed the problem of irrelevant features, noise, and dimensionality in a dataset, which can inhibit how the classification algorithm performs. In machine learning, feature selection approaches are critical, particularly in the context of credit card fraud detection, where relevant feature selection is critical. We use techniques such as machine learning algorithms, data mining techniques, and data science to stop and detect credit card fraud. These algorithms often classify genuine and fraudulent transactions in credit card datasets. However, the challenge of high dimensionality and irrelevant features persists, hindering improvements in classifier algorithms. This study centered on detecting credit card fraud (CCF) using a Modified Binary Bat Algorithm (MBBA) for feature selection. The MBBA selects the most informative features to improve the classifier algorithm's performance. The classifier algorithms used in this research are Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT). We conducted the experiment using the Python programming language, and the results indicate that RF achieves 99.945% accuracy, SVM 99.847%, and DT 99.909%. As a result, RF has the best accuracy. In summary, the optimal performance of a classification algorithm depends on the selection of relevant features for credit card fraud detection. The paper suggests improving the effectiveness of classifier algorithms for credit card fraud detection by employing the Modified Binary Bat algorithm, which outperforms the Genetic Algorithm (GA) in feature selection