LEP-Model: Ascertain Loan Predictions Using ML Approach

Abstract: As a result of the banking industry's advancements, a large number of people are applying for bank loans. However, the bank can only approve a limited number of applicants due to its limited resources, so determining who will be a safer candidate for approval is a common procedure. We therefore attempt to lower the risk involved in choosing the safe individual in this study report in order to preserve numerous bank endeavors and assets. This is accomplished by taking information from the previous records of the borrowers and based on these records, the machine was trained using an ML and Python model to provide the most accurate results. Assigning a debt to a particular individual or not is the primary goal of this study article. With the Logistic Regression algorithm receiving the maximum score of 80.78%, our research result demonstrated good performance accuracy. Finding out if it will be safe to give a loan to a specific individual is the first priority. The principal objective of the research paper is to forecast the loan eligibility of the clients and ascertain the conditions that precluded them from obtaining a loan for the construction of their own home.

Keywords: Loan Prediction, Machine Learning, Logistic Regression, Banking Sector.