University of Twente Student Theses
Explainable AI in finance
Pantov, A.I. (2024) Explainable AI in finance.
|
PDF
1MB |
| Abstract: | The demand for models that are interpretable and transparent is on the rise as Artificial Intelligence (AI) is getting more widely used. When discussing AI in the financial sector, making decisions is supposed to be effective, but most importantly, it must be done openly and responsibly. The need for models to be interpretable is especially crucial in this industry for various reasons, including regulatory compliance, trust and reliability and informed decision-making. The central theme of this paper is an examination of the common applications and methodologies of Explainable AI (XAI) in the financial industry. Different aspects of finance are explored, and various commonly used XAI techniques are identified. This study analyzes relevant research articles through a systematic literature review focusing on the application and types of XAI methods. The results show that XAI is widely applied in fields such as credit risk assessment, fraud detection, stock market forecasting and customer profiling. Another finding from the examined literature is that SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) are solidified as the de facto industry standard for XAI currently. Thus, such research assists to introduce more developments within finance for XAI while highlighting major trends, gaps and future directions that need to be addressed in future studies. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 01 general works, 54 computer science, 83 economics |
| Programme: | Business & IT BSc (56066) |
| Link to this item: | https://purl.utwente.nl/essays/100969 |
| 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