The Predictive Power of 'Head-and-Shoulders' Price Patterns in the U.S. Stock Market

Abstract

We use the pattern recognition algorithm of Lo et al. (2000) with some modifications to determine whether "head-and-shoulders" price patterns have predictive power for future stock returns. The modifications include the use of filters based on typical price patterns identified by a technical analyst. With data from the S&P 500 and the Russell 2000 over the period 1990-1999 we find little or no support for the profitability of a stand-alone trading strategy. But we do find strong evidence that the pattern had power to predict excess returns. Risk-adjusted excess returns to a trading strategy conditioned on "head-and-shoulders" price patterns are 5-7 percent per year. Combining the strategy with the market portfolio produces a significant increase in excess return for a fixed level of risk exposure.

Keywords: kernel regression, stock prices, technical analysis

JEL Classification: G1, G11, G14