The 45% drop in the US equity markets has caused even stalwarts to question the wisdom of the "buy and hold" strategy. But rule-based approaches for deciding when to buy or sell suffer the same problem. Sometimes they work and sometimes they don't. In this presentation, Dr. Mike Bowles shows how familiar data-mining tools can be used to derive a robust algorithmic trading system.
A simple rule-based approach trend-following system serves as a starting point. He looks at that system's characteristics and then employs a neural net to predict which of the system's trades should be taken and which ones should be skipped.
Bowles demonstrates that this significantly improves the performance of the trading system (Sharpe's ratio of 1.6 to Sharpe’s ratio 3.6). This example illustrates one way in which data mining tools have proven useful to practitioners of quantitative finance.
Bio
Michael Bowles
Michael Bowles is self employed writing and deploying fully automated trading systems. These systems blend traditional and modern mathematical and machine learning techniques to achieve robustness while being completely algorithmic. Michael has also founded two successful Silicon Valley startups and worked as senior scientist and project manager at Hughes Aircraft Satellite Division.
He held the C. Start Draper Chair in Aeronautical Engineering at MIT subsequent to earning his ScD in signal processing from MIT. He also holds an MBA from UCLA where he concentrated in finance and new venture initiation. See also: http://www.linkedin.com/in/mikebowles
Since giving this talk a year ago, I've made numerous changes to the general approach of using machine learning to improve trading results. If you're interested to talk about them, send me an email mike@mbowles.com.