Explainable neural network for pricing and universal static hedging of contingent claims

作者：

Highlights：

• A neural network-based algorithm for pricing of contingent claims with early exercise feature.

• Desirable property of interpretability of the network.

• Interpretation leads to a universal approach for static hedging of contingent claims.

• Numerical examples for multi-dimensional options with different payoffs.

摘要

•A neural network-based algorithm for pricing of contingent claims with early exercise feature.•Desirable property of interpretability of the network.•Interpretation leads to a universal approach for static hedging of contingent claims.•Numerical examples for multi-dimensional options with different payoffs.

论文关键词：Universal static hedging,Neural network,American Monte Carlo,Regress later

论文评审过程：Received 17 June 2021, Revised 26 October 2021, Accepted 3 November 2021, Available online 21 November 2021, Version of Record 21 November 2021.

论文官网地址：https://doi.org/10.1016/j.amc.2021.126775