Hong, S. R., Hullman, J., & Bertini, E. (2020). Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs. Proceedings of the ACM on Human-Computer Interaction, 4, 1-26.
https://doi.org/10.1145/3392878

has been cited by the following article:

• TITLE: Explainable Machine Learning in Risk Management: Balancing Accuracy and Interpretability

  AUTHORS: Mengdie Wang, Xuguang Zhang, Yongbin Yang, Jiyuan Wang

  KEYWORDS: Explainable Machine Learning, Risk Management, Accuracy, Interpretability, Decision-Making, Transparency, Risk Assessment, Machine Learning in Finance, Fraud Detection, Credit Scoring, SHAP, LIME

  JOURNAL NAME: Journal of Financial Risk Management, Vol.14 No.3, July 14, 2025

  ABSTRACT: Machine learning (ML) has revolutionized risk management by enabling organizations to make data-driven decisions with higher accuracy and speed. However, as machine learning models grow more complex, the need for explainability becomes paramount, particularly in high-stakes industries like finance, insurance, and healthcare. Explainable Machine Learning (XAI) techniques, such as LIME (Local Interpretable Model-agnostic Explanations) and SHAP (Shapley Additive Explanations), address this challenge by providing transparency into the decision-making processes of machine learning models. This paper explores the role of XAI in risk management, focusing on its application in fraud detection, credit scoring, and market forecasting. It discusses the importance of balancing accuracy and interpretability, considering the trade-offs between model performance and transparency. The paper highlights the potential of XAI to improve decision-making, foster trust among stakeholders, and ensure regulatory compliance. Finally, the paper discusses the challenges and future directions of XAI in risk management, emphasizing its role in building more transparent, accountable, and ethical AI systems.