Dynamic Replication and Hedging: A Reinforcement Learning Approach
Kolm, Petter N. and Gordon Ritter. "Dynamic Replication and Hedging: A Reinforcement Learning Approach." The Journal of Financial Data Science 1.1 (2019).
Posted: 5 Dec 2018 Last revised: 16 Mar 2021
Date Written: November 11, 2018
We address the problem of how to optimally hedge an options book in a practical setting, where trading decisions are discrete and trading costs can be nonlinear and difficult to model. Based on reinforcement learning, a well-established machine learning technique, our model is shown to be flexible, accurate and very promising for real-world applications.
Keywords: Finance; Hedging; Investment analysis; Machine learning; Optimal control; Options; Portfolio optimization; Reinforcement learning
JEL Classification: G11, C61
Suggested Citation: Suggested Citation