Ensemble learning for portfolio valuation and risk management

We introduce an ensemble learning method for dynamic portfolio valuation and risk management building on regression trees. We learn the dynamic value process of a derivative portfolio from a finite sample of its cumulative cash flow. The estimator is given in closed form. The method is fast and accurate, and scales well with sample size and path space dimension. It can also be applied to Bermudan options. Numerical experiments show good results for examples in dimensions 12 and 36.