Mining Fool's Gold

Abstract

This paper is a light hearted version of our paper forthcoming in the Financial Analysts Journal. We investigate the popular Motley Fool Foolish Four portfolio as a case study in data mining--the practice of developing trading strategies by searching through databases for correlations and patterns. The performance of the Foolish Four portfolio is documented and used to illustrate the mistaken inferences that can plague any investment research project. Using the Foolish Four case study, we show that data mining can be detected by the complexity of the trading rule, the lack of a coherent story or theory, the performance of out-of-sample tests, and the adjustment of returns for risk, transaction costs, and taxes. Finally, we document that the Foolish Four and Dow Ten trading rules have become popular enough to influence selected stock prices at the turn of the year.