A Novel Approach for Bank Loan Approval by Verifying Background Information of Customers through Credit Score and Analyze the Prediction Accuracy using Random Forest over Linear Regression Algorithm

Authors

  • Ch.Venkata Sandeep
  • T. Devi

DOI:

https://doi.org/10.47750/pnr.2022.13.S04.211

Keywords:

Machine Learning, Novel Random Forest, Linear Regression, Mean Accuracy, Credit Risk, Bank loan.

Abstract

Aim: To analyze the accuracy of Novel Random Forest (RF) and Linear Regression Algorithm (LR) algorithms used to approve bank loans. Materials and Methods: The existing model uses Linear Regression Algorithm (LR) and the proposed model employs a Novel Random Forest (RF). The Random Forest is a supervised learning model, it constructs solutions for different regression problems. It provides a high rate of accuracy by crossvalidation. The 20 sample values are used to find out the Mean, Std. Deviation and Std. error means. The sample size was measured as 40 per group using G power (80%). Results: The resultant graph explains the comparison of the mean accuracy values of algorithms Novel Random Forest (RF) and Linear Regression (LR) where the mean accuracy of the Novel random forest is about 70.5% and the mean accuracy value of the Linear Regression is about 69.5%. The significance obtained is p=1.0 that is p>0.05, it shows insignificance between the groups based on independent sample T-Test. Conclusion: The mean accuracy rate of the Novel Random Forest algorithm has been improved to 70.5% compared to Linear Regression which is having around 69.5% mean accuracy.

Downloads

Published

2022-10-07

Issue

Section

Articles

How to Cite

A Novel Approach for Bank Loan Approval by Verifying Background Information of Customers through Credit Score and Analyze the Prediction Accuracy using Random Forest over Linear Regression Algorithm. (2022). Journal of Pharmaceutical Negative Results, 1748-1755. https://doi.org/10.47750/pnr.2022.13.S04.211