Bank Loan Approval using Machine Learning

Abstract

The bank loan decision-making process is a complex algorithmic procedure that combines the applicant's financial situation, creditworthiness, and loan meaning with the bank's threat assessment as well as lending requirements, thereby allowing access to funds for borrowers while handling the bank's financial risk. Bank loan approval has been affected by linear regression or Gaussian Naive Bayes, but these algorithms are constrained by overfitting and underfitting. The decision tree format also adds clarity and readability. The selection of the decision tree classifier facilitates the estimation of loan approval. A decision tree classification system can be a useful tool to predict whether or not a bank loan application will be approved despite these drawbacks. The experimental findings reveal that the suggested model decision tree classifier reaches 95% accuracy with a loss of 0.09%. This study presents a potentially useful method for predicting the bank loan approval in today’s dynamic corporate environment.