Extending application of explainable artificial intelligence for managers in financial organizations

Abstract

Anomalies are a significant challenge for businesses in all industries. Artificial intelligence (AI) based machine learning (ML) detection models can help find aberrant customer transaction behaviour in financial datasets. However, the output responses provided by these AI-based ML models lack transparency and interpretability, making it challenging for financial managers to comprehend the reasoning underlying the AI detections. Suppose managers cannot comprehend how and why AI models develop responses based on the input information. In such cases, AI is unlikely to enhance data-driven decision-making and add value to organizations. This article’s primary objective is to illustrate the capacity of the SHapley Additive exPlanations (SHAP) technique to give finance managers an intuitive explanation of the anomaly detections AI-based ML models generate for a specific customer transaction dataset. Theoretically, we contribute to the literature on international finance by offering a conceptual review of AI algorithmic explainability. We discuss its implications for sustaining a competitive advantage using the concepts of action design research methodology following the research onion framework. We also suggest an explainable AI implementation methodology based on SHAP as a valuable guide for finance managers seeking to boost the transparency of AI-based ML models and to alleviate trust difficulties in data-driven decision-making.