Credit risk modeling is undoubtedly among the most crucial issues in the field of financial risk management. With the recent financial turmoil and the regulatory changes introduced by the Basel accords, credit risk modeling has been receiving even greater attention by the financial and banking industry. Credit risk is the risk that a borrower or obligor defaults and does not honor the obligations to service debt. It can occur when the obligor is unable to pay or cannot pay on time. There can be many reasons for a default. In most cases, the obligor is in a financially stressed situation or refuses to comply with the debt service obligation, for example in the case of a fraud or a legal dispute.
In this course, we will decompose credit risk into three components: PD (probability of default), LGD (loss given default) and EAD (exposure at default).
- The probability of default measures the probability that an obligor will default typically in the upcoming year. Since it is a probability, it ranges between 0 and 1.
- The loss given default is the ratio of the loss on an exposure due to default of an obligor to the amount outstanding. It is also a number between 0 and 1.
- The exposure at default then represents the outstanding exposure at the time of capital calculation. It is measured in currency amount.
In this course, we will model PD, LGD, and EAD using a multilevel architecture. First, we will start by preparing the data. This includes selecting, sampling and preprocessing the data needed for modeling. In a second step, we will create a model to distinguish obligors in terms of their default, loss, or exposure risk. This will be followed by another step in which we will define default, loss, and exposure ratings, and calibrate the corresponding risk measures. Finally, we will also discuss how to validate and stress test the credit risk models developed.
Over 100,000 people subscribe to our newsletter.
See stories of Analytics and AI in your inbox.
The course is offered in collaboration with SAS. The course focusses on the concepts and modeling steps rather than the software. For registration and more information see:
For an interview with the instructor about the course content see:
Professor Bart Baesens is a professor at KU Leuven (Belgium), and a lecturer at the University of Southampton (United Kingdom). He has done extensive research on big data & analytics, customer relationship management, web analytics, fraud detection, and credit risk management. His findings have been published in well-known international journals (e.g. Machine Learning, Management Science, IEEE Transactions on Neural Networks, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Evolutionary Computation, Journal of Machine Learning Research, …) and presented at international top conferences. He is also author of the books Credit Risk Management: Basic Concepts (http://goo.gl/T6FNOn) , published by Oxford University Press in 2008; and Analytics in a Big Data World (goo.gl/k3kBrB), published by Wiley in 2014. His research is summarized at www.dataminingapps.com. He also regularly tutors, advises and provides consulting support to international firms with respect to their analytics and credit risk management strategy.