Performance of evolving trading strategies with different discount factors

We use an evolving prediction model based on the idea of minority games in which traders continuously evaluate a complete set of trading strategies with different memory lengths using the strategies´ past performance, weighted by a discount factor, and choose the strategy with the best past performance. Based on the chosen trading strategy they determine their prediction of the movement of each individual asset for the following time period. We find empirically using stocks from the S&P500 that our prediction model yields a success rate and trading return that is increasing the smaller the discount factor becomes. We hypothesize that this result is driven by the existence of complex patterns of returns that are constantly changing and thus cannot be captured by relying on long-lasting experiences or static trading strategies.