2019/12/31 by Sebastian Becker, Patrick Cheridito, Arnulf Jentzen · 2 citations
Economics, Econometrics and Finance · #q-fin.CP
paper · pdf · doi:10.3390/jrfm13070158
published as Journal of Risk and Financial Management 13, 7 (2020)
arxiv created 2020/07/18 · arxiv updated 2021/03/23
In this paper we introduce a deep learning method for pricing and hedging American-style options. It first computes a candidate optimal stopping policy. From there it derives a lower bound 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 different specifications of a Bermudan max-call option. In all cases it produces highly accurate prices and dynamic hedging strategies with small replication errors.