Pricing and hedging American-style options with deep learning
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.
Code (1)
Tasks
Deep LearningSimilar Papers 제목 키워드 기반
Arbitrage-free pricing of American options in nonlinear markets
We re-examine and extend the findings from the recent paper by Dumitrescu, Quenez and Sulem (2018) who studied American and game options in a particular market model using the nonlinear arbitrage-free pricing approach de…
No-arbitrage and hedging with liquid American options
Since most of the traded options on individual stocks is of American type it is of interest to generalize the results obtained in semi-static trading to the case when one is allowed to statically trade American options. …
KANOP: A Data-Efficient Option Pricing Model using Kolmogorov-Arnold Networks
Inspired by the recently proposed Kolmogorov-Arnold Networks (KANs), we introduce the KAN-based Option Pricing (KANOP) model to value American-style options, building on the conventional Least Square Monte Carlo (LSMC) a…
Kolmogorov-Arnold NetworksArbitrage-Free Pricing of Game Options in Nonlinear Markets
The goal is to re-examine and extend the findings from the recent paper by Dumitrescu, Quenez and Sulem (2017) who studied game options within the nonlinear arbitrage-free pricing approach developed in El Karoui and Quen…
Simultaneous upper and lower bounds of American-style option prices with hedging via neural networks
In this paper, we introduce two novel methods to solve the American-style option pricing problem and its dual form at the same time using neural networks. Without applying nested Monte Carlo, the first method uses a seri…