Generating Realistic Economic Scenarios for Stress Testing Portfolios Using Generative AI

Home / Events / Industry Talks / Generating Realistic Economic Scenarios for Stress Testing Portfolios Using Generative AI

Generating Realistic Economic Scenarios for Stress Testing Portfolios Using Generative AI

Join Samit Ahlawat for a talk that showcases the ability of generative AI methods to handle the twin challenges of economic scenario generation – generating realistically evolving scenarios that can capture the breadth of potential but unforeseen periods of stress.

Samit Ahlawat
- My Current Time Zone - America/Detroit
- United Kingdom, London
- America/Detroit
- American Samoa, Pago Pago
- Argentina, Buenos Aires
- Australia, Melbourne/Sydney
- Bangladesh, Dhaka
- Brazil, Rio de Janeiro
- Canada, Vancouver
- Canada, St. John's
- Chile, Santiago
- Chile, Easter Island
- China, Beijing
- Egypt, Cairo
- Fiji, Suva
- France, Paris
- French Polynesia, Marquesas Islands
- Greece, Athens
- India, New Delhi
- Indonesia, Jakarta
- Iran, Tehran
- Japan, Tokyo
- Kenya, Nairobi
- Mexico, Mexico City
- Nepal, Kathmandu
- New Caledonia, Nouméa
- New Zealand, Auckland/Wellington
- Peru, Lima
- Portugal, Azores
- Russia, Vladivostok
- Saudi Arabia, Riyadh
- Singapore, Singapore
- South Korea, Seoul
- Sri Lanka, Colombo
- Thailand, Bangkok
- Tonga, Tongatapu
- Turkey, Istanbul
- UAE, Dubai
- United States, Denver
- United States, Honolulu
- United States, New York
Wed 12 Nov 2025
13:00 - 14:00 EST
Online

Book event / Sign up

Event Description

Financial regulatory agencies conduct periodic stress testing of systemically significant financial institutions to ensure they have the requisite capital to continue functioning as viable businesses during times of economic stress without jeopardizing the stability of the financial system. Manual design of these scenarios using historical data, exclusively or primarily, is hamstrung by the inherent limitations of historical experience, which may be inadequate to model unforeseen economic scenarios. To further compound the problem, correlations between macroeconomic variables may change and evolve in markedly different manner during those periods of economic malaise and a manual design of testing scenarios is likely to overlook those aspects of macroeconomic variable evolution. This talk will showcase the ability of generative AI methods to handle the twin challenges of economic scenario generation – generating realistically evolving scenarios that can capture the breadth of potential but unforeseen periods of stress.

Speaker

Samit Ahlawat

Samit Ahlawat currently works at Meta as a Machine Learning Engineer and has worked as a portfolio manager at QSpark Investment, specializing in US equity and derivative trading. He has extensive experience in quantitative asset management and market risk management, having previously worked at JP Morgan Chase and Bank of America. His research interests include artificial intelligence, risk management, and algorithmic trading strategies. Samit holds a master’s degree in numerical computation from the University of Illinois Urbana-Champaign. Samit has authored several research papers in artificial intelligence, finance, economics and numerical computation in addition to holding a patent for facial recognition technology. His research on using machine learning technologies to improve financial forecasting has enabled finance practitioners to leverage generative AI tools, such as variational auto-encoders (VAE), alongside statistical methodologies to model asset price distribution probabilities. Samit also mentors AI professionals at Kaggle and has delivered industry talks and presentations on artificial intelligence.