Implementation of Gradient Boosted Tree, Support Vector Machinery and Random Forest Algorithm to Detecting Financial Fraud in Credit Card Transactions

Abstract

According to Google Trends data, machine learning-based credit card identification has grown over the last five years, at the very least, across all nations. In order to detect credit card fraud in this study, the authors will use machine learning methods such random forests, support vector machines, and gradient-boosted trees. The authors used the Synthetic Minority Oversampling Technique (SMOTE) and Random Under Sampling (RUS) sampling methods in each algorithm to compare because there was a class imbalance in this investigation. The research findings demonstrate that the author's algorithm and sample technique were successfully used, as shown by the AUC values obtained for each being > 0.7. The top score in RUS was 0.7835 using the Random Forest algorithm, whereas the greatest score in SMOTE was 0.73 with the Gradient Boosted Trees approach. The Random Forest algorithm and the Random Under Sampling (RUS) technique are developed as a result of this research, and they are useful for identifying fraudulent credit card transactions.