An Innovative Method to Enhance the Accuracy of Credit Card Fraud Detection Using Logistic Regression Algorithm by Comparing Random Forest Algorithm

Abstract

Aim: The objective is to develop a model to predict which transactions could be fraud with a high accuracy rate by using machine learning(ML) methods, such as the innovative Random Forest Algorithm. Materials and Methods: F1 score and accuracy rate are performed on fraud rates transactions in a dataset. The two groups (LR) the sample size is (N=20) and (RF) is (N=20) with G power value = 80. Results: To perform the transactions in the credit card by utilizing the card number, financial balance and client details, and if it is offline, the fraud has to steal the user's details in online transactions, which is not easily recognized by the client and bank authority, which prompts loss of sensitive data. (p<0.05) statistically significant value is compared to the amount and time since last purchase with a confidence level of 95% (=.519). (RF) algorithm is used for detecting credit card fraud. The accuracy is analyzed based on the dataset of 99.3%, where the (LR) has the accuracy of 99.1%. Conclusion: The performance of strategy is measured based on accuracy, F1 score, Precision, Recall. The results seem to be better accuracy for (RF) is 93.3%.