Explaining reinforcement learning agent for high-frequency trading in quantitative finance
High-frequency trading (HFT) has emerged as a prominent domain within quantitative trading, leveraging advanced algorithms to exploit microsecond-level market inefficiencies, particularly evident in the volatile Cryptocurrency (Crypto) market. Despite its potential, HFT faces challenges such as low...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/174971 |
| _version_ | 1811693727650938880 |
|---|---|
| author | Zhao, Yuqing |
| author2 | Bo An |
| author_facet | Bo An Zhao, Yuqing |
| author_sort | Zhao, Yuqing |
| collection | NTU |
| description | High-frequency trading (HFT) has emerged as a prominent domain within quantitative trading, leveraging advanced algorithms to exploit microsecond-level market inefficiencies, particularly evident in the volatile Cryptocurrency (Crypto) market. Despite its potential, HFT faces challenges such as low data efficiency, dynamic market changes, complexity in decision-making, and a lack of explainability. In response, this study presents a novel approach rooted in Reinforcement Learning (RL) to enhance HFT’s efficiency and explainability. Leveraging a hierarchical Markov Decision Process (MDP) framework and integrating feature importance analysis methods, the proposed methodology demonstrates significant improvements in efficiency across various financial criteria, outperforming existing baselines. Furthermore, the incorporation of explainable methods enhances transparency, especially in complex decision-making scenarios. Observations from feature importance analysis shed light on critical market dynamics, informing trading strategies. Future work includes extending the proposed approach to low-frequency data, feature importance for out-of-distribution (OOD) detection and exploring predictive analysis of feature importance on price patterns, promising avenues for advancing quantitative finance strategies. |
| first_indexed | 2024-10-01T06:56:17Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/174971 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:56:17Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1749712024-04-19T15:46:34Z Explaining reinforcement learning agent for high-frequency trading in quantitative finance Zhao, Yuqing Bo An School of Computer Science and Engineering boan@ntu.edu.sg Computer and Information Science High-frequency trading Explainable AI Reinforcement learning Quantitative finance High-frequency trading (HFT) has emerged as a prominent domain within quantitative trading, leveraging advanced algorithms to exploit microsecond-level market inefficiencies, particularly evident in the volatile Cryptocurrency (Crypto) market. Despite its potential, HFT faces challenges such as low data efficiency, dynamic market changes, complexity in decision-making, and a lack of explainability. In response, this study presents a novel approach rooted in Reinforcement Learning (RL) to enhance HFT’s efficiency and explainability. Leveraging a hierarchical Markov Decision Process (MDP) framework and integrating feature importance analysis methods, the proposed methodology demonstrates significant improvements in efficiency across various financial criteria, outperforming existing baselines. Furthermore, the incorporation of explainable methods enhances transparency, especially in complex decision-making scenarios. Observations from feature importance analysis shed light on critical market dynamics, informing trading strategies. Future work includes extending the proposed approach to low-frequency data, feature importance for out-of-distribution (OOD) detection and exploring predictive analysis of feature importance on price patterns, promising avenues for advancing quantitative finance strategies. Bachelor's degree 2024-04-17T07:42:45Z 2024-04-17T07:42:45Z 2024 Final Year Project (FYP) Zhao, Y. (2024). Explaining reinforcement learning agent for high-frequency trading in quantitative finance. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/174971 https://hdl.handle.net/10356/174971 en SCSE23-0055 application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science High-frequency trading Explainable AI Reinforcement learning Quantitative finance Zhao, Yuqing Explaining reinforcement learning agent for high-frequency trading in quantitative finance |
| title | Explaining reinforcement learning agent for high-frequency trading in quantitative finance |
| title_full | Explaining reinforcement learning agent for high-frequency trading in quantitative finance |
| title_fullStr | Explaining reinforcement learning agent for high-frequency trading in quantitative finance |
| title_full_unstemmed | Explaining reinforcement learning agent for high-frequency trading in quantitative finance |
| title_short | Explaining reinforcement learning agent for high-frequency trading in quantitative finance |
| title_sort | explaining reinforcement learning agent for high frequency trading in quantitative finance |
| topic | Computer and Information Science High-frequency trading Explainable AI Reinforcement learning Quantitative finance |
| url | https://hdl.handle.net/10356/174971 |
| work_keys_str_mv | AT zhaoyuqing explainingreinforcementlearningagentforhighfrequencytradinginquantitativefinance |