University of Twente Student Theses
Explainable Reinforcement Learning (XRL) in Finance and in a Low-Predictability Betting Game
Murtaza, M.A. (2025) Explainable Reinforcement Learning (XRL) in Finance and in a Low-Predictability Betting Game.
|
PDF
294kB |
| Abstract: | In dynamic domains such as finance, where predicting outcomes is essential, introducing reinforcement learning (RL) has shown considerable potential but it remains largely unexplored due to the limited number of practical applications available and field limitation as of now. A key challenge in financial decision-making comes from the complexity and low predictability of financial systems, making it difficult to understand, evaluate, and trust these decisions. This is particularly relevant when integrating RL applications, as they mostly operate as black-box models, which lack transparency. The application of Explainable AI (XAI) and its techniques in RL comes as a promising solution. This research will analyze why and how XAI methods are used in the financial field in order to underline benefits and actual progress and results with a focus on their contribution to decision-making, risk assessment and regulatory compliance. Furthermore, it will make use of a simplified betting game as a case study in order to explore how Explainable Reinforcement Learning (XRL) can be used to improve explainability by examining and explaining decisions made by RL agents in an unpredictable financial environment. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science, 85 business administration, organizational science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/105092 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page