Announcement of the Spanish Society of Statistics and Operations Research – BBVA Foundation Awards 2025

The committee of the Spanish Society of Statistics and Operations Research (SEIO) – BBVA Foundation Awards 2024, meeting online on July 7th, 2024, and ratified by the SEIO Executive Board on July 9th, 2025, has decided to award the following prizes:

Best methodological contribution in Statistics

Daniel García Rasines (tenure-track Assistant Professor in quantitative methods at CUNEF University) and G. Alastair Young (professor of Statistics at Imperial College London, United Kingdom), for their paper Splitting strategies for post-selection inference, published in Biometrika.

The paper by Rasines and Young, published in Biometrika, addresses the challenge of conducting valid inference following model selection, introducing a pioneering randomization mechanism for post-selection inference. Through novel theoretical contributions, the authors establish the effectiveness of their approach in the Gaussian setting and derive a Central Limit Theorem applicable to non-Gaussian error distributions. The proposal overcomes the limitations of previous methods. Much of the existing methodology was computationally burdensome or restricted to a limited class of selection algorithms. In contrast, the method proposed in this paper offers a powerful and computationally light inferential framework which can be applied with a wider variety of selection mechanisms.

Best methodological contribution in Operations Research

Gorka Kobeaga (Data Scientist at CDM Consultores), Jairo Rojas-Delgado (Senior Software Developer Engineer at Archlet), María Merino (Associate Professor of Statistics and Operations Research at the University of the Basque Country) and Jose A. Lozano (Professor at the Department of Computer Science and Artificial Intelligence of the University of the Basque Country and at the Basque Center for Applied Mathematics, BCAM), for their paper A revisited branch-and-cut algorithm for large-scale orienteering problems, published in the European Journal of Operational Research.

This research, published in the European Journal of Operational Research, represents a substantial advancement in addressing the Orienteering Problem (OP), establishing a new benchmark in both computational efficiency and solution quality. These outcomes are achieved through a novel and rigorous problem formulation that integrates innovative cut-generation techniques and refined branching strategies, resulting in a more effective and scalable solution methodology.

Best applied contribution in Statistics

Jorge Castillo Mateo (Assistant Professor of Statistics and Operations Research at the University of Zaragoza), Alan E. Gelfand (James B. Duke Distinguished Professor Emeritus at Duke University, United States), Zeus Gracia Tabuenca (Assistant Professor of Statistics and Operations Research at the University of Zaragoza), Jesús Asín (Associate Professor of Statistics and Operations Research at the University of Zaragoza) and Ana C. Cebrián (Associate Professor of Statistics and Operations Research at the University of Zaragoza), for their article Spatio-Temporal Modeling for Record-Breaking Temperature Events in Spain, published in the Journal of the American Statistical Association.

The contribution by Castillo-Mateo et al., published in the Journal of the American Statistical Association, presents a rigorous and innovative statistical framework for modeling the occurrence of daily maximum temperature records in Spain. This work constitutes a substantial advancement in the study of extreme events related to climate change, offering a comprehensive and original modeling approach. It introduces spatio-temporal mixed-effects within a logistic regression framework, while also accommodating anisotropic conditions and long-term temporal trends. Furthermore, the accompanying R package enhances the accessibility and practical implementation of the methodology for applied researchers and practitioners.

Best applied contribution in Operations Research

Antonio Alonso Ayuso (Professor of Statistics and Operations Research at the Rey Juan Carlos University), Francisco Gortázar Bellas (Associate Professor of Computer Science and Artificial Intelligence at the Rey Juan Carlos University), Micael Gallego Carrillo (Associate Professor of Computer Science and Artificial Intelligence at the Rey Juan Carlos University), Javier Martín Campo (Associate Professor of Statistics and Operations Research at the Complutense University of Madrid), María Sierra-Paradinas (Data Scientist at Orquest) and Óscar Soto-Sánchez (Predoctoral Researcher at the Rey Juan Carlos University), for their project SOC: Flat Steel Cutting Optimisation System for Cortichapa, published in the European Journal of Operational Research; Computers and Industrial Engineering and Journal of Heuristics.

The contribution proposes a mathematical methodology to solve the slitting problem in a steel company, exemplifying a perfect combination of methodological innovation, practical relevance and societal impact. A mixed-integer linear programming model, combined with heuristic algorithms, is proposed for solving the highly complex cutting problems of the company. It is worth mentioning the reduction of leftovers generated in the entire process and the reduction of planning times, directly impacting industrial competitiveness and contributing to environmental sustainability.

Best contribution in Statistics and Operations Research applied to Data Science and Big Data

Santiago Mazuelas (Ikerbasque Research Associate Professor at the Basque Center for Applied Mathematics, BCAM), Yuan Shen (Professor at the Department of Electronic Engineering of Tsinghua University, China) and Aritz Pérez (Postdoctoral Researcher at the Basque Center for Applied Mathematics, BCAM), for their paper Generalized Maximum Entropy for Supervised Classification, published in IEEE Transactions on Information Theory.

The paper, published in IEEE Transactions on Information Theory, extends the maximum entropy principle to supervised classification, adapting a foundational idea in statistical inference and decision-making to this context. Using a robust approach in this generalized learning framework, the authors obtain minimax risk classifiers exhibiting a good performance and, at the same time, satisfying theoretical guarantees. These results can be of notable relevance for the researchers and practitioners in the fields of Data Science and Machine Learning, particularly in signal processing, neuroscience or natural language processing, enabling the comparison of different classifiers and the assessment of efficiency bounds under the same empirical framework.

Committee

The international committee has a membership proposed by SEIO and the BBVA Foundation. Chairing the committee on this occasion was Albert Satorra, Professor Emeritus of Statistics at Pompeu Fabra University and Research Professor at the Barcelona School of Economics. Its members were: Carlos Henggeler Antunes, Professor and Director of R&D at the Institute for Systems Engineering and Computers of the University of Coimbra (Portugal); Rosa Crujeiras Casais, Professor of Statistics and Operations Research at the University of Santiago de Compostela; Pinar Keskinocak, Professor and Chair of the H. Milton and Carolyn J. Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology (United States); Martine Labbé, Professor of Operations Research at the Université Libre de Bruxelles (Belgium); and Dimitris N. Politis, Distinguished Professor and Associate Director of the Halicioğlu Data Science Institute (Turkey).