Accuracy Analysis for Logistic Regression Algorithm and Random Forest Algorithm to Detect Frauds in Mobile Money Transaction

Authors

  • G. Manoj Kumar
  • Dr.M. Nalini

DOI:

https://doi.org/10.47059/revistageintec.v11i4.2182

Abstract

Aim: The main motto of the study is to detect the frauds in mobile money transactions using logistic regression and random forest algorithms and comparing their accuracy. Materials and Methods: Logistic regression (N=10) and random forest algorithm(N=10) was iterated 20 times and detected the frauds. Results and Discussion: Random forest has significantly better accuracy (99.6%) compared to logistic regression (92.6%). The statistical significance of random forest algorithm (p<0.018 Independent sample T-test) is high. Conclusion: Within the limits of this study, random forest algorithm offers better accuracy to detect frauds in mobile money transactions.

Downloads

Published

2021-07-11

Issue

Section

Articles