Performance Analysis of a Counter-intuitive Automated Stock-Trading Strategy (2003)
Ronggang Yu and Peter Stone
Autonomous trading in the stock market is an area of great interest in both academic and commercial circles. A lot of trading strategies have been proposed and practiced from the perspectives of Artificial Intelligence, market making, external data indication, technical analysis etc., The advent of computer and inexpensive data has given everyone the ability to test their trading ideas. This paper examines some properties of a counter-intuitive automated stock-trading strategy in the context of the Penn-Lehman Automated Trading (PLAT) simulator, which is a real-time, real-data market simulator. While it might seem natural to buy when the market is on the rise and sell when it's on the declining, our strategy does exactly the opposite. As a result, we call it the reverse strategy. The reverse strategy was the winner strategy in the first and second PLAT live competitions. In this paper, we analyze the performance of the reverse strategy: in what kinds of market, it will make profits or lose money. Also, we suggest ways to control the risk of using the reverse strategy in certain kinds of markets.
In Proceedings of the Fifth International Conference on Electronic Commerce, Pittsburgh, PA, October 2003.

Peter Stone Faculty pstone [at] cs utexas edu