Maio, 2023

Ter23Mai14:30DaSSWeb | Learning to Be Fair in Machine Learning with Mathematical OptimizationData Science and Statistics Webinar14:30 Evento VirtualTipo de evento:Online,WebinárioLocal:Faculdade de Economia


Dolores Romero Morales
Copenhagen Business School, Denmark

Decision Making has been dramatically impacted by Artificial Intelligence and Machine Learning. While state-of-the-art Machine Learning models provide excellent accuracy, they effectively work as black boxes. This lack of transparency, with complex functions expressing the relation between input (features) and the outputs (responses), challenges model validation. Furthermore, black boxes may hide unfair outcomes for risk groups in high stakes decision making such as medical diagnosis, allocation of social benefits, or approvals in parole hearings. In this presentation, we will navigate through some novel mathematical optimization techniques embedded in the construction of Machine Learning models to enhance their interpretability and fairness.

Short Bio
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, and has received various distinctions. Currently, she is Editor-in-Chief to TOP and an Associate Editor of Journal of the Operational Research Society, Omega and the INFORMS Journal on Data Science. She currently leads the EU H2020-MSCA-RISE NeEDS project with the aim to improve the state of the art in Data Driven Decision Making through intersectoral and international mobility.

Link Zoom