Comparative Analysis of Credit Card Fraud Detection using Logistic regression with Random Forest towards an Increase in Accuracy of Prediction

Abstract

The study aims to identify the frauds committed using a payment card such as credit cards, debit cards, and also an experiment is performed to find the best suitable algorithm among Random forest and Logistic Regression. Materials and Methods: To stop the fraud detections using Random forest (N=10) and Logistic regression (N=10) with supervised learning that gives insights from the previous data. Results: The precision of the random forest is 76.29% compared with Logistic regression with accuracy of 74.65% with statistical significance value p=0.03 (p<0.05) using Independent sample t test. Conclusion: This results proved that Random forest was significantly better for Fraud detection than Logistic regression within the study’s limits.