The prediction of initial returns on initial public offerings (IPOs) is a complex matter. The independent variables identified in the literature mix strong and weak predictors, their explanatory power is limited, and samples include a sizable number of outliers. In this context, we suggest that random forests are a potentially powerful tool. In this paper, we benchmark this algorithm against a set of eight classic machine learning algorithms. The results of this comparison show that random forests outperform the alternatives in terms of mean and median predictive accuracy. The technique also provided the second smallest error variance among the stochastic algorithms. The experimental work also supports the potential of random forests for two practical applications: IPO pricing and IPO trading.
random forest; initial public offering; prediction; underpricing; initial public offerings