Estimating stock price predictability using genetic programming
Minglei Duan, Richard J. Povinelli · 2001
A new method that quantifies the predictability of a stock’s price is presented. This new method overcomes some problems with previous approaches to stock price predictability. The new method shows which stocks are more predictable, and hence can help in making investment decisions. Genetic Programming is used as the modeling tool. Preliminary experiments are conducted to show the advantages of this method.