Does size matter? A genetic programming approach to technical trading

Introduced in 1970 by Eugene Fama, the Efficient Market Hypothesis (EMH) has become a central proposition in the finance literature. If EMH holds, any trading strategy that relies on the assumption that past prices contain information that can be used to consistently earn abnormal profits should be fallacious. The mere fact that technical analysis, or the use of past prices to infer private information, is a common and seemingly lucrative practice among investment professionals has inspired many researchers to investigate the profitability of technical trading rules. Numerous performance studies have been conducted over the years, with widely varying results. Much of this variation in results can be attributed to differences in testing procedures (see Park and Irwin 2004 for an extensive review of this literature).x It has been contended that small-cap stocks are priced in a less efficient manner than large-cap stocks (Blume et al. 1994), so that small-cap pricing errors can more readily be exploited. This is linked to the fact that such stocks are less widely held by portfolio managers and do not receive the same level of attention by financial analysts. The lower level of research being conducted on small-cap stocks would suggest that they are relatively more susceptible to information asymmetry, experiencing more gradual price adjustments as the news is more slowly assimilated, relative to large-cap stocks.