摘要：In this paper we introduce a deep learning method for pricing and hedging American-styleoptions. It first computes a candidate optimal stopping policy. From there it derives a lowerbound for the price. Then it calculates an upper bound, a point estimate and confidence intervals.Finally, it constructs an approximate dynamic hedging strategy. We test the approach on differentspecifications of a Bermudan max-call option. In all cases it produces highly accurate prices anddynamic hedging strategies with small replication errors.
