Abstract
Credit risk ratings consist of assessing the creditworthiness of the issuer and gauge the risks associated with buying its debt. Any delay in updating the credit risk ratings could have a severe impact on the financial system such as the financial crisis in 2008. This paper discusses a case that leverages emerging technology and breakthrough cognitive analytics in the financial industry. It specifically describes the design and implementation of a predictive modeling case based on the Machine Learning Approach and its application in credit risk forecasting and portfolio management. Using big data and Machine Learning, it is possible to improve credit risk analysis and forecasting by allowing the algorithms to search for patterns using large sets of data.
Highlights
During the 2008 financial crisis, credit rating updates were delayed which could have prevented bigger financial damages
The main goal of the task in Credit Rating Modeling is to have the classification into rating categories (9 in our case)
To test our model, seeing if it could be generalized in samples other than the training set, we should see how the model performs in the out-of-sample data, so-called model backtesting
Summary
During the 2008 financial crisis, credit rating updates were delayed which could have prevented bigger financial damages. These rating agencies have explored to leverage the rapid increase in the data availability and computing power added with Machine Learning (Bacham, 2017). Their focus was on small- and medium-sized borrowers in which they concluded that the Machine Learning models deliver a similar accuracy ratio as their other models, but they appeared more as a “black box”. Bankruptcy predictions have used similar techniques (Barboza, 2017) and in credit card risk management (Butaru et al, 2016) All these capabilities are focused on having a better financial system and on preventing another financial crisis
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
