Fraud Detection in Banking using the Kaggle Credit Card Dataset and XGBoost Model

The threat posed by credit card fraud, and by extension, online banking, continues to grow with the convenience brought forth by online banking services. Many financial institutions and customers stand at great risk because of this reality. The purpose of the paper is to enhance the security of banking systems through advanced technologies - machine learning. The research employed the well-known dataset from Kaggle Credit Card, which contains numerous records of transactions labeled as either fraud or not, thus presenting an aspect similar to real life imbalanced data. The main focus in the present work is the XGBoost model which involves one of the ensemble learning methods, which is characterized by a high level of precision and fast execution times. As a result of hyperparameter optimization and feature engineering, the paper also works on the performance of the algorithm improving its ability to detect fraudulent transactions in a sea of normal transactions. The results obtained from the experiments show that the XGBoost model is not only proven to be more accurate than earlier approaches to fraud detection, but also greatly reduces the number of false positives. This study not only contributes to the existing literature on detecting financial fraud but also represents the ways in which finance can benefit from machine learning to design secure systems within banking operations. The metrics in which the model suggested outperformed the available approaches are, the accuracy is 98.60%, error rate is 2.10% while its precision reached 95.40, recall of 92.30, F1 score 93.20 and AUC-ROC 99.70. This study not only contributes to the existing literature on detecting financial fraud but also represents the ways in which finance can benefit from machine learning to design secure systems within banking operations.