It’s the risk model! Alan Greenspan, former chairman of the Federal Reserve, testified before the House Committee on Oversight and Government Reform yesterday. The reason for his testimony was to try to shed some light on the current financial mess.
The ex-Fed Chairman blamed the mess on risk pricing models. Greenspan has long praised computer technology as a tool that can be used to limit risks in financial markets. But, it seems there was a catch.
Alan Greenspan testified, “In recent decades a vast risk management and pricing system has evolved based on the best insights of mathematicians and finance experts, supported by major advances in computer and communications technology.” He added, “The whole intellectual edifice, however, collapsed in the summer of last year because, the data inputted into the risk management models generally covered only the past two decades, a period of euphoria."
Alan Greenspan also opinioned that if the risk pricing models had been built to include "historic periods of stress, capital requirements would have been much higher and the financial world would be in far better shape today."
I guess the risk modelers didn’t read our page on Backtesting trading models. We have always said that you need to test your model or strategy over different market environments – bull and bear (both quiet and volatile) and trendless. To accomplish this, you must backtest your strategy over as long a time period as possible – 36 years or more. You must make sure each of the different market environments is present in your test results.
We’ve debated with different traders over the years on how much data is required to backtest risk management models. We can only say the proof is now obvious. When you backtest trading systems or models, use several decades of data.
