Research lines
Our research lines focus on developing innovative mathematical and computational solutions to address complex challenges across multiple domains. Reach out directly to line leaders for scientific collaboration.
Complexity measures
We develop tools and metrics to analyze and characterize data regarding feature overlap, class separability, and data geometry to improve machine learning models based on dataset properties.
Data visualization
We design tools to graphically represent complex multidimensional data, focusing on enhancing decision-making through effective and interactive visualizations.
Explainable machine learning
We focus on explainable and interpretable ML, particularly counterfactuals and semifactuals, enhancing transparency in sensitive fields like healthcare and finance.
Foundations of machine learning
We explore the theoretical foundations of machine learning, specializing in Support Vector Machines, kernel methods, statistical learning theory, and ensemble methods.
Generative AI
We research and develop AI systems capable of generating realistic data, including text, images, and synthetic datasets, enabling personalization, simulation, and creative applications.
Indicator development
We design robust indicators for sectors like sustainable tourism and healthcare, supporting precise evaluations and informed public decisions.
Intelligent agents
We create autonomous and multi-agent AI systems for dynamic tasks, integrating perception, reasoning, and action for advanced automation.
Internet of things
We develop edge ML algorithms for IoT systems, optimizing data transmission to improve energy efficiency and operational reliability in smart sensors.
Knowledge-based systems
We create systems integrating domain expert knowledge, semantic graphs, and rule engines to address complex reasoning problems efficiently.
Metaheuristics
We research advanced heuristic and metaheuristic search algorithms to solve NP-hard combinatorial optimization problems in logistics and network design.
Open data
We develop architectures and systems for managing open data repositories, ensuring accessibility, interoperability, and reusability for public and scientific value.
Optimization
We develop mathematical optimization methods to maximize system efficiency in resource management, scheduling, and operational performance under uncertainty.
Performance metrics
We create advanced mathematical metrics to evaluate the efficiency, calibration, fairness, and generalization of complex machine learning models.
Sports analytics
We apply machine learning models to enhance athletic performance and competition strategies, across sports like football, swimming, and speed skating.
Recommender systems
We design personalized recommendation algorithms for tourism, content platforms, and clinical protocols, enhancing user decision-making.
Interested in launching a joint research initiative?
We collaborate with academic teams and institutions across Europe and Latin America.