Authors:

Jiaxuan Li

Date Created:

Not specified

Course Title:

Professor:

Not specified

About Paper:

Loans are the core business of banks. Banks' main profit comes directly from the loan's interest. This project analyzed important factors that cause a loan applicant to have bad credit risk, such as loan duration, Checking Account Balance, Age, etc. This is important for commercial banks to decide whether to grant loans to applicants and reduce financial losses due to loan defaults and bad credit risk. The motivation for this work is the rise in bad credit and loan losses among major banks during COVID. I built several models such as Nominal Logistic Regression model, K-Nearest Neighbors model, Classification Tree model, and Support Vector Machine to predict whether a loan applicant will have bad credit risk. My prediction model also provides potential business value. I will estimate how much bad credit cost our prediction model will save for the bank based on the confusion matrix. My predictive modeling and predictive analytics not only help commercial banks strengthen their credit risk management/prediction systems and reduce loan losses. It can also give future loan applicants a basis of exactly what parts of their information will be vital to the loan approval process.

Source:

Purdue University / 2023

Topics:

No topics listed

Co-authors:

Jiaxuan Li