Multi-period financial stress testing: an integrated risk view
Models are increasingly used in today's risk and business applications for a growing range of purposes within banks: automated credit decision making, capital measures, provisioning, stress testing, ... We make a tour on the different type of credit and portfolio risk models. These models range from simple linear formulations to non-linear additive models, decision trees and neural network techniques.
Practical information:
Want to register?
- Register until: 02 Jun 2022
- Price: Free
Registration is not necessary, you can simply join the seminar.
Would you like to receive a reminder of our monthly seminars in this series on time series? Subscribe!
Georganiseerd door:
Leertraject
Regression, survival and classification models support the individual
credit assessment, Markov chain models are used in the portfolio risk
assessment. On top of technical performance requirements, business
requirements concern a.o. readability, interpretability and stability. A
strong governance framework is applied to limit model risk.
The application of these models is illustrated on capital planning and macro-economic stress testing.
Teacher / speaker
Tony Van Gestel
Dr. ir. Tony Van Gestel obtained his PhD on mathematical modeling in 2002 at the Department of Electrical Engineering, Leuven Catholic University. His academic research focused on linear and nonlinear modeling techniques in time series and classification with applications in marketing, energy consumption and banking. After his PhD, he focused further on the banking applications when joining a large European bank to develop credit risk models on wholesale and retail portfolios. Next, more models were developed for stress-testing, credit valuation models, risk monitoring and portfolio risk modeling. He currently combines the management role of the Risk Models, Quantification and Default team with the CEO role of an subsidiary. In his free time, his research interests
focus on big data and machine learning. He co-authored 2 books and 40+ journal articles.
AI for Time Series
Several research groups in the Flanders AI Research Program conduct world-class research on time series, both in the development of algorithms and tools, as in a wide area of application fields. In a recent poll in the Flanders AI community, ‘time series’ came up as the most wanted topic for future workshops or courses. With this seminar series, we bring together researchers that are interested in, or are conducting research related to, time series. We offer a varied program of national and international speakers.
Klik on the separate webinars below to (re)watch the recordings.
Related courses
HPC Café
Seminarie - Online, Karlsruhe - KIT, HammerHAI, Training geselecteerd in de Belgische AI Factory Antenna (AIFA)
