报告题目：Unveiling the Path to Desired Predictions: An Explainability Approach for Black-Box Models

报告所属学科：工商管理

报告人：Xuefei Lu（SKEMA Business School, France）

报告时间：2026年5月13日 10:00-13:00

报告地点：经管学院705室

报告摘要：

As the wide adoption of machine learning models continues to spread across diverse decision-making systems, the inherent opacity of these models calls for interpretability. While established explainable machine learning methods provide insights into individual predictions, they encounter some implementation challenges. Among these challenges is the extrapolation issue, which arises from reliance on infeasible data points, as well as a deficiency in providing actionable guidance. This talk discusses various explainable methods that address these obstacles. Additionally, we introduce a novel approach combining counterfactuals and Shapley value, aimed at revealing actionable guidance regarding the desired trajectory of prediction changes. By applying this methodology across multiple datasets, a diverse range of technical and managerial insights is presented.

报告人简介：

Xuefei Lu is an Associate Professor at SKEMA Business School, France. She holds a PhD in Statistics from Bocconi University (Italy) and has previously worked as a post-doctoral researcher at Politecnico di Milano (Italy) and as a lecturer at the University of Edinburgh (UK).

Her research focuses on explainable artificial intelligence, statistical machine learning, and uncertainty quantification, with publications appearing in journals such as Operations Research, European Journal of Operational Research, Decision Analysis, Reliability Engineering & System Safety, etc. Her works have received international awards, among which the 2023 INFORMS Clemen-Kleinmuntz award and Runner-Up of 2024 SAS Data Mining Best Paper Award.

She is actively involved in academic service, serving on the editorial board of the European Journal of Operational Research and on the scientific committee of the Sensitivity Analysis of Model Output (SAMO) community. She is also a council member of the INFORMS Decision Analysis Society and a frequent reviewer for top-tier journals.