Ke Nian, PhD candidate
David R. Cheriton School of Computer Science
We propose a robust encoder-decoder model based on Recurrent Neural Network (RNN) for the data-driven option hedging problem. This approach naturally incorporates features selection. Using S&P 500 index option market data for more than a decade ending on August 31, 2015, we demonstrate that the daily hedging performance of the proposed model surpasses that of the minimum variance quadratic hedging formula, corrective methods based on LVF and SABR, and the data-driven model based on kernel learning framework. In addition, we demonstrate that the weekly and monthly hedging performance of the proposed model significantly surpasses that of the data-driven model based on kernel learning framework and Black-Scholes model with implied volatility.
200 University Avenue West
Waterloo, ON N2L 3G1