This paper implements a Cellular Genetic Algorithm (CGA) to compare key statistics on the earnings of a population of investors with different learning and innovation rates, defined as crossover and mutation rate, respectively. The data used was the adjusted closing price for the S&P Index 500, ‘INX’, from two low volatility periods-from 2004 to 2007, and from 2014 to 2017- and a relatively high volatility period-from 2008 to 2011-. This study concluded that there exists a significant difference when investors learn from performing peers and that optimal learning rates may vary between high and low volatility periods, being particularly beneficial in the former ones.
