Plenaries & Keynotes

State-of-the-art Artificial Intelligence (AI) and Machine Learning (ML) algorithms have become ubiquitous across industries due to their high predictive performance. However, despite their widespread deployment, these models are often criticized for their lack of transparency and accountability. Their “black-box” nature obscures the reasoning behind decisions, limiting trust and hindering their use in critical, data-driven decision-making processes. Moreover, algorithmic decisions can perpetuate or amplify societal biases, leading to unfair and discriminatory outcomes. These concerns are especially pressing in high-stakes domains such as healthcare, criminal justice, credit scoring, and public benefits, where algorithmic decisions can significantly affect individuals’ lives.

In Explainable Artificial Intelligence (XAI), local explanations seek to shed light on the prediction of a machine learning model at a given instance. Popular methodologies include LIME, which builds an interpretable surrogate model that approximates predictions around the instance, and SHAP, which attributes the difference between the instance prediction and a baseline prediction to individual features. While such explanations are valuable to the individuals affected by a prediction, they provide limited information to modelers and decision-makers seeking to understand model behavior across many individuals. This raises broader questions concerning which features drive explanations across groups of instances, whether explanations are consistent and fair across individuals, and how individuals with similar explanations can be identified and represented collectively. This presentation shows how Operations Research provides a natural framework for addressing these questions and moving from individual explanations toward explainability at the group level.

About Dolores Romero Morales

Dolores Romero Morales is a Professor in Operations Research at Copenhagen Business School. Her areas of expertise include Data Science, Supply Chain Optimization and Revenue Management. In Data Science she investigates explainability/interpretability, fairness and visualization matters. In Supply Chain Optimization she works on environmental issues and robustness. In Revenue Management she works on large-scale network models. Her work has appeared in a variety of leading scholarly journals, including European Journal of Operational Research, Management Science, Mathematical Programming and Operations Research. She has received various distinctions, such as the SEIO Medal for an outstanding contribution to the Operations Research discipline, and since June 2025, she is President-Elect of EURO – The Association of European Operational Research Societies.

Dolores has received funding from the EU as well as national research councils to conduct her research. She has worked with and advised various companies on these topics, including IBM, SAS, KLM and Radisson Edwardian Hotels, as a result of which these companies managed to improve some of their practices. SAS named her an Honorary SAS Fellow and member of the SAS Academic Advisory Board. Currently, she is a member of the Editorial Board of the International Journal of Production Research, and an Associate Editor of Journal of the Operational Research Society, the INFORMS Journal on Data Science, and TOP-Transactions in Operations Research.

Dolores joined Copenhagen Business School in 2014. Prior to coming to Copenhagen Business School, she was a Full Professor at University of Oxford (2003-2014) and an Assistant Professor at Maastricht University (2000-2003). She has a BSc and an MSc in Mathematics from Universidad de Sevilla and a PhD in Operations Research from Erasmus University Rotterdam.