Date of Award:

5-2022

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Computer Science

Committee Chair(s)

Curtis Dyreson

Committee

Curtis Dyreson

Committee

Hengda Chen

Committee

Rakesh Kaundal

Abstract

With the gradual end of the COVID-19 outbreak and the gradual recovery of the economy, more and more individuals and businesses are in need of loans. This demand brings business opportunities to various financial institutions, but also brings new risks. The traditional loan application review is mostly manual and relies on the business experience of the auditor, which has the disadvantages of not being able to process large quantities and being inefficient. Since the traditional audit processing method is no longer suitable some other method of reducing the rate of non-performing loans and detecting fraud in applications is urgently needed by financial institutions.

In this project, a financial risk control model is built by using various machine learning algorithms. The model is used to replace the traditional manual approach to review loan applications. It improves the speed of review as well as the accuracy and approval rate of the review. Machine learning algorithms were also used in this project to create a loan user scorecard system that better reflects changes in user information compared to the credit card systems used by financial institutions today. In this project, the data imbalance problem and the performance improvement problem are also explored.

Share

COinS