Learning sequential option hedging models from market data

Abstract

Following a direct data-driven approach, we propose a robust encoder-decoder Gated Recurrent Unit (GRU), GRU δ , for optimal discrete option hedging. The proposed GRU δ utilizes the Black-Scholes model as a pre-trained model and incorporates sequential information and feature selection. Using the S&P 500 index European option market data, we demonstrate that the weekly and monthly hedging performance of the proposed GRU δ significantly surpasses that of the data-driven minimum variance (MV) method, the regularized kernel data-driven model, and the SABR-Bartlett method. In addition, the daily hedging performance of the proposed GRU δ also surpasses that of MV methods based on parametric models, the kernel method, and SABR-Bartlett method.