Credit risk model management
View AgendaKey reasons to attend
- Explore the impact of Basel 3.1 and International Financial Reporting Standard 9 (IFRS 9) on credit risk modelling
- Learn how to develop a robust model validation framework
- Discover stress-testing techniques for credit risk portfolios across diverse economic scenarios
Customised Solutions
Does your team require a tailored learning solution on this or any other topic?
Working with the portfolio of expert tutors and Risk.net’s editorial team, we can develop and deliver a customised learning to make the most impact for your team, from initial assessment to final review.
About the course
This course provides insights into the effective management of credit risk models, focusing on the latest Basel 3.1 and IFRS 9 requirements. Participants will deepen their understanding of key estimation techniques, learn best practices in stress-testing across portfolio types and explore strategies for adapting models to economic shifts.
Through discussions on AI applications in credit risk modelling and guidance on model validation, attendees will learn to enhance model accuracy and transparency. The course also covers essential governance practices, including risk appetite, policy development and adherence to evolving regulatory standards.
Subject matter experts will address the unique challenges posed by both high- and low- default portfolios, equipping participants with the skills to optimise risk frameworks and build resilience in today’s dynamic economic landscape.
Avoid the price increase - book by December 31, 2024
Save up to $1,000*. Use promo code ‘LOCK24’ at checkout or contact us at learning@risk.net for more details.
Pricing options:
- Early-bird rate: save up to $800 per person by booking in advance (refer to the booking section for the deadline)
- 3-for-2 rate: save over $2,000 by booking a group of three attendees (applicable to this course)
- Subscriber reward: save 30% off the standard rate if you are a Risk.net subscriber (use code SUB30)
- Season tickets: save over $1,000 per person by booking 10 or more tickets (available on selection of courses)
*T&Cs apply
Learning objectives
Examine the evolving landscape of model risk management
Leverage artificial intelligence (AI) and machine learning to improve model accuracy
Discuss estimation techniques for high- and low-default portfolios
Explore strategies for handling missing scoring data and ratings assessments
Investigate the challenges associated with low-default portfolios under stress
Discover best practices for developing a credit risk appetite
Who should attend
Employees whose job responsibilities may include but are not limited to:
- Credit risk
- Risk modelling
- Risk management
- Model risk management
- Machine learning
- stress testing
Agenda
February 11–13, 2025
Live online. Timezones: Emea/Americas
Sessions:
- Introduction to credit risk model management and regulatory landscape
- Credit risk modelling developments
- Credit risk modelling post-IFRS 9
- Stress-testing credit risk portfolios
- Application of AI and machine learning in credit risk modelling
- Credit risk model validation
July 15–17, 2025
Live online. Timezones: Emea/Americas
Sessions:
- Introduction to credit risk model management and regulatory landscape
- Credit risk modelling developments
- Credit risk modelling post-IFRS 9
- Stress-testing credit risk portfolios
- Application of AI and machine learning in credit risk modelling
- Credit risk model validation
Tutors
Jonathan Schachter
CEO
Delta Vega Inc
Jonathan is a Berkeley-trained physicist and Columbia mathematician/statistician. He has spent over a quarter century in financial services, working in a range of institutions including banks, asset management firms, of which big four firms. He is a regulatory quant and provides weekly global online trainings in financial risk management. He is co-author of first ever model risk management textbook. He has experience in a spectrum of derivatives, structured products, counterparty credit risk, correlation credit risk, VaR, PFE, xVA, operational risk, portfolio risk, artificial intelligence and machine learning risk.
Daniel Eklove
Managing Director, Credit Models & Methodology
RBC
Daniel is a data scientist specialising in financial modelling, risk methodologies and treasury analytics. He also has project management experience in banking and insurance. His background includes studying health sciences before moving towards actuarial science and mathematical finance. He is currently leading a team of credit risk modellers mandated with both the development and implementation of models used in management and regulatory reporting. He also looks after the research, documentation and deployment of state-of-the-art model methodologies and predictive analytics.
Christian Marini
Associate Partner
Prometeia
Christian has a long experience as a leading consultant in the quantitative risk management modelling space, working in collaboration with primary financial and non-financial institutions as well as public companies, including local and central Banks. His expertise includes both technical knowledge in the development of credit risk methodologies and credit risk architecture systems, as well as commercial acumen gained in developing international markets within the risk management space.
Grigoris Karakoulas
President
InfoAgora Inc
Grigoris has over 26 years of experience in predictive modelling and risk management. He is the president and founder of InfoAgora that provides risk management consulting and more to financial services organisations. He is an adjunct professor in the department of computer science at the University of Toronto.
Prior to founding InfoAgora, Grigoris was working at CIBC as vice president of customer behavior analytics, responsible for customer decisioning and credit risk measurement solutions for adjudicating new customers and proactively managing existing ones. He has been a postdoctoral fellow in the Institute of Information Technology at the National Research Council. He is on the PRIMA subject matter boards for stress-testing and enterprise risk management and has published more than 40 papers in journals and conference proceedings. He holds a PhD in computer science.
Pre-reading materials
The Risk.net resources below have been selected to enhance your learning experience:
- Analyzing credit risk model problems through natural language processing-based clustering and machine learning: insights from validation reports
- Emerging lessons from the current credit risk cycle
- Can CRE credit risk models cope with hybrid working?
A Risk.net subscription will provide you access to these articles. Alternatively, register for free to read two news articles a month.