Option pricing and hedging with market friction using reinforcement learning

This paper presents a discrete European option pricing and hedging model under an environment with market friction using Q-Learning in Reinforcement Learning. The research novelty lies in the comparison of performance by various transaction cost models. Reinforcement Learning is implemented with the...

Full description

Bibliographic Details
Main Author: Jiang, Zixing
Other Authors: Bo An
Format: Final Year Project (FYP)
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/181126
_version_ 1826130285743308800
author Jiang, Zixing
author2 Bo An
author_facet Bo An
Jiang, Zixing
author_sort Jiang, Zixing
collection NTU
description This paper presents a discrete European option pricing and hedging model under an environment with market friction using Q-Learning in Reinforcement Learning. The research novelty lies in the comparison of performance by various transaction cost models. Reinforcement Learning is implemented with the Q-Learning Black Scholes (QLBS) model. This model is not only presented as an alternative to the canonical Black Scholes (BS) Model, but also offered as an extension to pricing models that commonly overlook realistic market conditions. The QLBS model is augmented to account for the trader’s risk aversion, transaction costs and market impact costs to reflect a risk-adjusted price and an optimal hedge. The baseline BS model is then used as a benchmark to illustrate the how the QLBS model can address the practical considerations of a trader’s hedging needs. The performance of two solutions, namely Dynamic Programming and Fitted Q Iteration, will be evaluated. By going model free and retaining the model’s simplicity solely built on linear algebra, this data driven approach can depart the academic limit of the Black Scholes continuous time framework and be extended as a practical tool for further strategy testing and optimisation.
first_indexed 2025-03-09T15:19:11Z
format Final Year Project (FYP)
id ntu-10356/181126
institution Nanyang Technological University
language English
last_indexed 2025-03-09T15:19:11Z
publishDate 2024
publisher Nanyang Technological University
record_format dspace
spelling ntu-10356/1811262024-11-15T11:39:51Z Option pricing and hedging with market friction using reinforcement learning Jiang, Zixing Bo An College of Computing and Data Science boan@ntu.edu.sg Computer and Information Science Option pricing Option hedging This paper presents a discrete European option pricing and hedging model under an environment with market friction using Q-Learning in Reinforcement Learning. The research novelty lies in the comparison of performance by various transaction cost models. Reinforcement Learning is implemented with the Q-Learning Black Scholes (QLBS) model. This model is not only presented as an alternative to the canonical Black Scholes (BS) Model, but also offered as an extension to pricing models that commonly overlook realistic market conditions. The QLBS model is augmented to account for the trader’s risk aversion, transaction costs and market impact costs to reflect a risk-adjusted price and an optimal hedge. The baseline BS model is then used as a benchmark to illustrate the how the QLBS model can address the practical considerations of a trader’s hedging needs. The performance of two solutions, namely Dynamic Programming and Fitted Q Iteration, will be evaluated. By going model free and retaining the model’s simplicity solely built on linear algebra, this data driven approach can depart the academic limit of the Black Scholes continuous time framework and be extended as a practical tool for further strategy testing and optimisation. Bachelor's degree 2024-11-15T11:39:51Z 2024-11-15T11:39:51Z 2024 Final Year Project (FYP) Jiang, Z. (2024). Option pricing and hedging with market friction using reinforcement learning. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181126 https://hdl.handle.net/10356/181126 en application/pdf Nanyang Technological University
spellingShingle Computer and Information Science
Option pricing
Option hedging
Jiang, Zixing
Option pricing and hedging with market friction using reinforcement learning
title Option pricing and hedging with market friction using reinforcement learning
title_full Option pricing and hedging with market friction using reinforcement learning
title_fullStr Option pricing and hedging with market friction using reinforcement learning
title_full_unstemmed Option pricing and hedging with market friction using reinforcement learning
title_short Option pricing and hedging with market friction using reinforcement learning
title_sort option pricing and hedging with market friction using reinforcement learning
topic Computer and Information Science
Option pricing
Option hedging
url https://hdl.handle.net/10356/181126
work_keys_str_mv AT jiangzixing optionpricingandhedgingwithmarketfrictionusingreinforcementlearning