Nested Stochastic Simulations: Bridging Risk & Pricing Models

Nested stochastic simulations – where one stochastic process is affected by other variables that also have stochastic processes, requiring simulations within simulations – have become more important to both insurance and banking practitioners in recent years. Driven by changes in regulations and accounting standards, as well as advances in risk management best practices, nested stochastics are utilized in a broad range of applications – from Solvency II, to calculating future Greeks for hedge strategy projections, to Brute Force Potential Future Exposures (PFE) on exotic derivatives.

A number of proxy techniques exist to reduce computational requirements, such as replicating portfolios, cluster analysis, or Least Squares Monte Carlo. Despite the obvious benefits of such techniques, however, brute force nested simulation is still required to validate these approaches. In many cases, such as Future Greeks for variable annuities, brute force nested simulation is required to achieve desired levels of accuracy.

But this is easier said than done – practitioners face formidable challenges in implementing a robust nested stochastic framework, most notably in terms of computational complexity and model consistency. How can practitioners maintain model consistency between two stochastic frameworks with different measures, for example when a risk neutral pricing model is nested within a real world risk model? How can practitioners test and validate their proxy methods using a brute force approach?

On Wednesday, April 8th, 2015 featured speaker Alex Marion, Vice President of Product Management at Numerix discussed the best practices for creating nested stochastic frameworks and showed how practitioners can overcome many of the implementation challenges they face.

Mr. Marion covered:

  • Uses cases for nested stochastic modeling
  • Challenges and limitations of current approaches
  • Bridging risk and pricing models of different measures
  • Implementing generic, dynamic cash flow models within a nested stochastic framework
  • Stochastic simulation of nested market consistent valuations and Greeks
  • Comparison to algorithmic exposures (Least Squares Monte Carlo)

Featured Speakers


Want More from Numerix?

Subscribe to our mailing list to stay current on what we're doing and thinking at Numerix