Defaulter Prediction for Assessment of Credit Risks using Machine Learning Algorithms

摘要

The examination of credit risk has become very crucial in the financial world to avoid massive losses, as, without repayment of loans, they earn no profit. It can be thought of as an expansion of the credit distribution measure. To ease the task of investors, a methodology is proposed using machine learning models that can predict the status of whether the loan should be granted to a customer based on his pre-fed attributes. first, preprocessing of the data is performed followed by feature extraction using LDA and PCA. The model is created using various machine learning algorithms on two different sized datasets. It has been observed that Logistic regression shows the highest accuracy followed by random forest classification and KNN. It is also seen that LDA performed better than PCA in all algorithms. Therefore, machine learning regression and classification algorithms have shown reliable results for the money-lenders to safely invest.