Modeling Investor Behavior Using Machine Learning: Mean-Reversion and Momentum Trading Strategies

Figure 1

Heatmap showing average daily investment changes (%) in 2016 broken down by investor’s gender (a) and education degree (b). We take average values of investment decisions that took place in every weekday within the month. Due to the existence of some large absolute values and to improve readability, we winsorize the investment variation distribution by 5% at each side before taking the average.

(a)

(b)