Automated Loan Approval System using Machine Learning

In today's world, it's common for people to apply loans from banks and financial institutions for various reasons. But not everyone who applies can be approved. We often hear about cases where individuals fail to repay their loans, causing significant losses for banks. Making decisions about loan approvals is risky and challenging. Previous works considered single algorithm to make predictions where accuracy is low. To enhance the accuracy is a challenge. So, the goal of this study is to use multiple machine learning algorithms to extract key information about the loan data which could help organizations make better decisions about approving or rejecting loan requests from customers. In this paper, we analyze real bank credit data and apply various machine learning algorithms to determine the creditworthiness of customers. The accuracies of 56.28%, 59.46%, 57.34%, 63.23%, and 73.79% are obtained for logistic regression, support vector machine, Decision tree classifier, Random Forest Classifier, and ensemble method respectively. The aim of this work is to train a machine learning model to predict the eligibility for the applied loan and to create an interface for different types of loans.