Generating trading rules on the stock markets with genetic programming

Technical analysis is aimed at devising trading rules capable of exploiting short-term 2uctuations on the 3nancial markets. Recent results indicate that this market timing approach may be a viable alternative to the buy-and-hold approach, where the assets are kept over a relatively long time period. In this paper, we propose genetic programming as a means to automatically generate such short-term trading rules on the stock markets. Rather than using a composite stock index for this purpose, the trading rules are adjusted to individual stocks. Computational results, based on historical pricing and transaction volume data, are reported for 14 Canadian companies listed on the Toronto stock exchange market. ? 2003 Elsevier Ltd. All rights reserved.