Loan Prediction Using Random Forest Algorithm

Authors

  • Sukkala Tharun Kumar Goud
  • Mohammed Shoaib
  • Satya Bharadwaj
  • Y. Sreenivasulu

Abstract

With the growth of the banking sector, more and more people are applying for bank loans. All of these loans are not allowed. The principal income of bank assets arises from the interest earned on the loan. Bank profit or loss depends largely on the amount of the loan, i.e., whether customers pay off the loan or fail. The main purpose of banks is to invest their assets in secure customers. Today, many banks approve loans after a number of verifications and verification processes but yet there is no guarantee that the selected customer is safe or not. By predicting defaulters, the bank can reduce its non-performing Assets. This makes a study of this situation very important. Previous research in this period has shown that there are many ways to learn the problem of controlling loan default. But as appropriate predictions are very important for increase in profit, it is important to study the type of different methods and their comparisons. A very important method in predictive analysis is used to study the problem of predicting those who fail to borrow money. It is therefore important to use a variety of strategies in the banking sector to select a customer who pays the loan on time. In this report, we use a random forest algorithm to separate the data. The random forest algorithm creates a model from a trained database and this model is used in test data and we obtain the required output.

Published

2022-04-30