Posted by Quicksilver under
Quant ,
Trading[3] Comments
Given that the big news is the big market down day (and, as I write, the aftershock), I figured it was the perfect time to try some of the concepts I learned in Why?Stock Markets Crash. Sornette provides a non-linear model formula that he attempts to fit to markets and notes that when this model finds a good fit, it often does so right before major crashes. This concept relates directly to talks of singularities. Basically, exponential growth, peppered with log-periodic (equally spaced on a log chart but closer and closer together on a standard chart)?waves, results in a singularity or critical time where a crash is highly likely.
There are several parameters that need to be optimized and, since it’s non-linear, it requires some major computation power. All those parameters make it more difficult because, during fitting, you happen upon local minima that?aren’t the real best minimum. So you have to run the optimization several times with different starting seed values and hopefully converge on the answer.
So enter Java. I wrote a program that would read in market data (S&P 500 since the ’03 bottom) and try to perform a fit to the model. (more…)