Abstract
Credit risk analysis and making accurate investment and lending decisions has been a challenge for the financial industry for many years, as can be seen with the 2008 financial crisis. However, with the rise of machine learning models and predictive analytics, there has been a shift to increased reliance on technology for determining credit risk. This transition to machine learning comes with both advantages, such as potentially eliminating human error and assumptions from lending decisions, and disadvantages, such as time constraints, data usage inabilities, and lack of understanding nuances in machine learning models. In this paper, I look at four different machine learning models developed in the past few years specifically for credit analysis. I will explore their effectiveness and the factors and datasets they individually use. I then summarize how my analysis on these models can be used by future researchers to both develop new machine learning models for credit risk analysis and find more potential analysis options, along with how this research could help with increased reliance of machine learning in the financial industry on a broader scale.
Faculty Advisor/Mentor
Rui Ning
Document Type
Paper
Disciplines
Artificial Intelligence and Robotics | Finance and Financial Management | Information Security
DOI
10.25776/t85r-bt14
Publication Date
2022
Upload File
wf_yes
Included in
Artificial Intelligence and Robotics Commons, Finance and Financial Management Commons, Information Security Commons
Understanding the Effectivity and Increased Reliance of Credit Risk Machine Learning Models in Banking
Credit risk analysis and making accurate investment and lending decisions has been a challenge for the financial industry for many years, as can be seen with the 2008 financial crisis. However, with the rise of machine learning models and predictive analytics, there has been a shift to increased reliance on technology for determining credit risk. This transition to machine learning comes with both advantages, such as potentially eliminating human error and assumptions from lending decisions, and disadvantages, such as time constraints, data usage inabilities, and lack of understanding nuances in machine learning models. In this paper, I look at four different machine learning models developed in the past few years specifically for credit analysis. I will explore their effectiveness and the factors and datasets they individually use. I then summarize how my analysis on these models can be used by future researchers to both develop new machine learning models for credit risk analysis and find more potential analysis options, along with how this research could help with increased reliance of machine learning in the financial industry on a broader scale.