Towards Responsible AI for Financial Transactions
Charl Maree, Jan Erik Modal, Christian W. Omlin
Abstract
The application of AI in finance is increasingly dependent on the principles of responsible AI. These principles-explainability, fairness, privacy, accountability, transparency and soundness form the basis for trust in future AI systems. In this empirical study, we address the first principle by providing an explanation for a deep neural nenvork that is trained on a mixture of numerical, categorical and textual inputs for financial transaction classification. The explanation is achieved through (1) a feature importance analysis using Shapley additive explanations (SHAP) and (2) a hybrid approach of text clustering and decision tree classifiers. We then test the robustness of the model by exposing it to a targeted evasion attack, leveraging the knowledge we gained about the model through the extracted explanation.