All Black Boxes Eventually Crash
- Thread starter zdreg
- Start date
I'm a black box. I have traded the exact same for years, and I have only blown up once.
Let's be clear this article is referring specifically to models which try to be hedged / neutral to a large variety of weird risk factors; not to all automated / systematic trading. I don't believe there is anything wrong with those models, but:
I recently listened to a podcast with some all-star [there are awards for everything now] “Black Box” equity trader. His confidence was staggering considering the general unpredictability of the future and, of course, the equity markets. He explained how he had completely converted from a generally unsuccessful, discretionary technical trading style to a purely quantitative and scientific trading mode. He seemed to be so excited that his models, according to him, were pretty much “bullet proof”.
My answer to a different question; all traders (blackbox, other systematic or discretionary) who think their models are bullet proof, will eventually crash.
Years of monthly returns with exceedingly low volatility were turned “inside out” in just 4-6 weeks as many funds suffered monthly losses > 20% which was previously considered highly improbable and almost technically impossible
Second question; all traders (blackbox, systematic or discretionary) whose models consistently make steady returns will eventually see a large loss (negative skew).
GAT
(extremely pessimistic systematic trader, whose models make steady losses with occasional large profits [positive skew])
I recently listened to a podcast with some all-star [there are awards for everything now] “Black Box” equity trader. His confidence was staggering considering the general unpredictability of the future and, of course, the equity markets. He explained how he had completely converted from a generally unsuccessful, discretionary technical trading style to a purely quantitative and scientific trading mode. He seemed to be so excited that his models, according to him, were pretty much “bullet proof”.
My answer to a different question; all traders (blackbox, other systematic or discretionary) who think their models are bullet proof, will eventually crash.
Years of monthly returns with exceedingly low volatility were turned “inside out” in just 4-6 weeks as many funds suffered monthly losses > 20% which was previously considered highly improbable and almost technically impossible
Second question; all traders (blackbox, systematic or discretionary) whose models consistently make steady returns will eventually see a large loss (negative skew).
GAT
(extremely pessimistic systematic trader, whose models make steady losses with occasional large profits [positive skew])
nobody leaves a good fishing hole when the fish are still biting
Depends on the model.
A high frequency model with holding periods of less than a second will probably work for a few months at best (although providing liquidity to the market will always pay). But there is tons of data to refit it regularly.
A low frequency model with holding periods of weeks or months should work "forever". It needs decades of data to fit, and you should be using models that are robust over multiple business cycles.
GAT