Machine Learning Techniques in Model Risk Management

Webinar Recording To celebrate our most recent Risk.net Technology Award 2020, we invite you to rewatch the webinar “Machine Learning techniques in Model Risk Management (MRM)”. At this webinar, Jos Gheerardyn, CEO of Yields.io, talked about the interplay between Machine Learning (ML) and Model Risk. Firstly, we discussed how Machine Learning can help to streamline validation tasks, […]

Machine Learning Techniques in Model Risk Management

Webinar Recording

To celebrate our most recent Risk.net Technology Award 2020, we invite you to rewatch the webinar “Machine Learning techniques in Model Risk Management (MRM)”.

At this webinar, Jos Gheerardyn, CEO of Yields.io, talked about the interplay between Machine Learning (ML) and Model Risk. Firstly, we discussed how Machine Learning can help to streamline validation tasks, such as measuring data quality, creating challenger models and performing stress tests. Moreover, the second half of the talk covered how to create a model risk management (MRM) framework for Artificial Intelligence (AI).

Agenda

Introduction: About Chiron

Part I: Managing Model Risk with AI
  • Validating Data
  • Data Generation
  • Model Risk Quantification
  • Monitoring
Part II: Managing the risk of AI
  • Model dependencies
  • Safe AI framework
  • Model assumptions and design
  • Performance testing
  • Limitations

Chiron

Our award-winning platform, Chiron, is primarily designed to support the full model lifecycle with the purpose to improve model risk management. In other words, Chiron provides dedicated analytical support for all three lines of defence, while simultaneously fostering collaboration between various teams, organization of the work through model and data inventories and integration with workflow engines.

Regarding the analytical support, Chiron is primarily designed to automate and speed up model validation and model testing tasks, to generate regulatory compliant documentation and to industrialize model monitoring. Furthermore, the platform works with all models that are used within the financial sector such as credit decision models, AI applications, valuation algorithms, market risk, AML and behavioural models.

In addition, Yields.io provides a wide range of advisory services (model risk and data governance, model risk framework design, managing risk of AI applications) as well as technical consulting (model validation, testing, model risk framework implementation, integration services) always centred around Chiron. We focus on the team, empowering them not only with technology but also with knowledge through training on the applications and its programming languages.

Speaker

Jos Gheerardyn has built the first FinTech platform that uses AI for real-time model testing and validation on an enterprise-wide scale. A zealous proponent of model risk governance & strategy, Jos is on a mission to empower quants, risk managers and model validators with smarter tools to turn model risk into a business driver. Prior to his current role, he has been active in quantitative finance both as a manager and as an analyst.

Over the past 15 years, he has been working with leading international investment banks as well as with award-winning start-up companies. He is the author of multiple patents applying quantitative risk management techniques to imbalance markets. Jos Gheerardyn holds a PhD in superstring theory from the University of Leuven, Belgium.

Do you have questions about the webinar? Send us an email.

Interested in learning more? Watch a demo of Chiron, our flagship product.