Date: 29 September 2020
Author: FINTECH Circle & BCMstrategy
Automated, AI-powered scenario analysis enhances the risk management process by accelerating the ability to assess multiple potential shifts in risk profiles. From high level macro analysis to targeted parameter shifts, risk managers and portfolio managers can pinpoint previously unanticipated portfolio vulnerabilities and hedge exposures more precisely regarding default probabilities, loss given default, liquidity, and correlations.
However, the pandemic era creates breaks in time series data from which AI-powered processes learn. Data gaps from delayed reporting are amplified by major fiscal and monetary policy support structures which alter the shape of credit risk. Using pre-pandemic credit risk data can undermine the effectiveness of AI-driven scenarios.
In this webinar, the speakers discuss the main data gaps and options for adjusting training data. We will also illustrate how to incorporate data derived from the public policy process during 2020 so that AI-driven scenario analysis can become more accurate using current – not historical – data. Case studies will include examples from the credit risk, trade/global macro, and central bank digital currency/payments contexts.
- Assess how AI processes can deliver more effective scenario analysis processes
- Identify and adjust for pandemic-related time series breaks
- Incorporate public policy structured data
- Look at the case studies: credit risk, trade/global macro, central bank digital currency/payments
The webinar is now available on-demand here.
Barbara C. Matthews
Founder and CEO
CEO and Founder