Building a Better Risk Model
In a world where counterparty credit risk is important, wrong-way risk occurs when credit exposure and the probability of default increase together. Its counterpart, right-way risk, occurs when credit exposure decreases as the probability of default increases. Financial regulators and industry thought leaders have been aware of the danger of wrong-way risk for more than a decade, and there is a reasonably robust body of literature describing methodologies for modeling directional-way risk, which comprises both right- and wrong-way risk.
But when Ignacio Ruiz and his coauthors, Piero Del Boca and Ricardo Pachón, looked at the current models for directional-way risk, they found that the models were impossible to calibrate. So, they set about creating their own model.
In the March/April 2015 issue of the Financial Analysts Journal, Ruiz and his coauthors explain the genesis of their new directional-way risk model in their article, “Optimal Right- and Wrong-Way Risk from a Practitioner Standpoint.” I got the chance to talk with Ruiz about his team’s research.
The researchers call their model the “empirical analysis methodology.” They argue that the empirical analysis methodology is the optimal way to model directional-way risk because it is based on a robust modeling framework that uses the observed dependency structure between the counterparty default events and the value of the portfolio of derivatives for that counterparty, as opposed to a guess of what that dependency structure might be. The empirical analysis methodology can be directly and easily calibrated to new data.
Ruiz notes that “the thinking process for the other approaches was along the lines of, ‘OK, these are the features I want to model, let me construct a mathematical theory to describe them.’” But his team took a different path. Ruiz says that they asked, “What is the information out in the market that we can actually see?” This approach is more in line with the titular “practitioner standpoint,” and it led Ruiz and his colleagues to create a methodology based more on empirical data rather than on mathematical abstractions.
CFA Institute members can read the full article on the Publications website.
If you liked this post, don’t forget to subscribe to the Enterprising Investor.
All posts are the opinion of the author. As such, they should not be construed as investment advice, nor do the opinions expressed necessarily reflect the views of CFA Institute or the author’s employer.
Photo credit: ©iStockphoto.com/retrorocket