Stress Testing

Stress testing has long been a powerful arrow in the hedge fund and asset manager’s quiver to test how their portfolios may react in extreme market, geopolitical or macro-economic events. Ten years after the financial crisis, the practice of combining statistical models with stress tests has become the norm, but designing the right stress test remains as much art as science. Which stress test - historical, user-defined or transitive? Which risk factors? What best practices should you employ to meet your objectives?

Axioma Stress Testing Best Practices

We offer clients the most sophisticated and comprehensive stress testing framework on the market, with multifaceted scenario, time span and correlation views of portfolio risk. Our clients use Axioma-designed stress testing best practices to derive the most value out of their testing regimen:

  1. Determine a purpose-fit stress test. Selecting the right stress test for your portfolio is as fundamental to risk management as selecting the right canvas is to painting a masterpiece–get it wrong and all subsequent considerations have little to no value.
  2. Know when to use historical stress test. The best practice is to use it if you believe the historical event will repeat.
  3. Use transitive (correlated) and user-defined (isolated) stress tests together.
  4. Update your stress tests regularly to reflect changing market conditions and portfolio composition.
  5. Leverage multi-horizon and instantaneous stress tests in combination to view differences for nonlinear positions and when portfolio aging in an important consideration.
  6. Employ diagnostics for beta analysis and to detect highly correlated core factors.
  7. Fine-tune inputs to enhance event-related analysis. Select the most appropriate pricing and risk factors for the portfolio.

> Learn more best practices

Axioma Offers Multiple Types of Stress Tests

What's the Future of Stress Testing?

We are researching how machine learning techniques can help construct smarter stress tests. Our advanced-learning algorithms are looking at how specific inputs, such as exposures, risk statistics, structural trades and more, can recommend the stress test design and test period that would yield the most intuitive results. This would reduce your time to develop and construct stress tests and means you can run tests more frequently for timely insight into your portfolio risk.


> Read more about our approach to dynamic stress tests


Contact Axioma today to learn how we can help you make better informed investment decisions through stress testing


Research paper: Reverse Stress Testing Challenges: Toward a Systematic Framework

Blog post: The Art of Designing a Stress Test For Market Risk: A Step-By-Step Approach

Blog post: Enhanced Transitive Stress Testing: The Dynamic Difference

Research paper: Stress Testing Best Practices

Research paper: Toward Dynamic Stress Tests