Real World Algorithmic Exposure: An In-Depth Exploration with Case Study Examples
On March 2, 2016 featured speaker Dr. Ping Sun, built on his previous presentation introducing Real World Algorithmic Exposure and took a deep dive into the innovative new resampling approach, outlining the theory behind it along with showcasing examples of resampling in action and a comparison of the Algorithmic Exposure and Brute Force approaches.
Real World risk metrics, such as Potential Future Exposure (PFE) or Expected Exposure profiles, are heavily used in counterparty credit risk functions within banks and feature in regulatory capital requirements. The market standard for these calculations has been the computationally intensive nested Monte Carlo approach, in which the Brute Force simulations can require billions of simulation paths and substantial computing power.
In order to handle real world PFE and other counterparty exposure calculations in a single framework, which requires risk neutral pricing on top of real world scenarios, an innovative decoupling approach relaxes the requirement that the same model be used to both generate scenarios and simulate the future values. This method, based on Las Vegas Monte Carlo simulations with new resampling techniques, provides a much more efficient alternative to Real World nested Monte Carlo exposure calculations, decreasing computation time by several orders of magnitude.
On March 2, 2016 featured speaker Dr. Ping Sun, Executive Director of Financial Engineering at Numerix, built on his previous presentation introducing Real World Algorithmic Exposure and took a deep dive into the innovative new resampling approach, outlining the theory behind it along with showcasing examples of resampling in action and a comparison of the Algorithmic Exposure and Brute Force approaches.
DR. SUN ADDRESSED THE FOLLOWING:
- Real World Models
- Real World vs. Risk Neutral Models
- Examples of Real World Models
- Real World Algorithmic Exposures for Advanced Risk Measures
- Theory of Resampling
- Model Independent Decoupling Approach
- Resampling Example
- Algorithmic Exposure vs. Nested Monte Carlo Approach
- Resampling vs. Monte Carlo on Monte Carlo
- Comparison and Contrast with an Example
To view the on-demand webinar, just register on the right side of this page.
Featured Speakers
Ping Sun, PhD
Dr. Sun, PhD is Senior Vice President, Financial Engineering at Numerix. He is also product manager of the Numerix CrossAsset analytics platform. During his career at Numerix, Dr. Sun’s work has appeared in number of publications and academic journals, and he has been showcased as a lecturer at a range of academic events and industry conferences. Dr. Sun served as a consultant to Lehman Brothers as a FX / EQ Desk Quant, and his extensive experience includes working to develop the Numerix cross-currency Economic Scenario Generator. He earned a Doctorate Degree in Physics from City College of New York, and a Master’s Degree and Undergraduate Degree in Physics from Fudan University in Shanghai, China.
Greg Murray
Greg Murray is responsible for increasing awareness of the Numerix brand in financial markets around the globe, as well as conducting strategic industry research for different departments within Numerix. Previously, he oversaw product and field marketing initiatives at the company, and he started his tenure in a sales role. Prior to Numerix, Mr. Murray worked in derivative analytics sales roles at other software firms, and he held derivative trading positions for seven years as an option market-maker and proprietary trader across a variety of asset classes.
