A Fraudulent Transaction Prediction in Credit Card by Using Novel LGBA over LR Algorithms

Abstract

The Research is to predict the accuracy of credit card fraudulent transactions using the Light Gradient Booster algorithm.Novel Light Gradient Booster with sample size =10 then Logistic Regression of sample size = 10 were executed for estimating accuracy rate of credit card fraudulent transactions. The sigmoid functions used in Light Gradient maps the values between 0 and 1. Light Gradient Booster Algorithm has a Maximum accuracy (91.6%) while comparing to the performance of Logistic Regression (81.4%). There was a statistical significance difference between Light Gradient Booster and Logistic Regression with p = 0.0001 (p<0.05) based on 2-tailed analysis. Light Gradient algorithm helps in predicting with better accuracy percentage of credit card fraudulent transaction than Logistic regression.