About KNODIS
KNOwledge Discovery & Information Systems (KNODIS) is a research group based at the Universidad Politécnica de Madrid (UPM). Our research lies at the intersection of machine learning and data science, with a strong focus on both theoretical foundations and applied solutions that address real-world challenges.
Within this broad domain, our core lines of work include recommender systems, where we develop algorithms to personalize user experiences; deep learning, where we explore neural architectures for complex data representations; and combinatorial optimization, where we design intelligent techniques to solve high-dimensional and computationally hard problems efficiently. These areas are not only fundamental in artificial intelligence but also highly impactful across industries such as e-commerce, healthcare, logistics, and education.
Given our university’s commitment to teaching excellence, KNODIS is also deeply engaged in educational innovation. We actively participate in the design and implementation of new methodologies and tools to improve teaching and learning processes, particularly in technology and engineering education.
KNODIS has a strong and sustained research trajectory, with dozens of peer-reviewed publications in leading international journals and conferences. Our members frequently collaborate with other academic institutions and participate in national and European research projects. We also maintain an active and ongoing collaboration with industry partners, promoting the transfer of knowledge and technology to solve practical problems and create societal value.
Through this blend of cutting-edge research, innovation in teaching, and industrial collaboration, KNODIS contributes to the advancement of artificial intelligence while fostering the development of skilled professionals and impactful technological solutions.
Members
Research group leader
- Dr. Fernando Ortega (fernando.ortega@upm.es)
Research team
- Dr. Santiago Alonso (santiago.alonso@upm.es)
- Dra. Sandra Arranz Paraiso (sandra.paraiso@uam.es)
- Dra. Gema Bello (gema.borgaz@upm.es)
- Dr. Alberto Díaz-Álvarez (alberto.diaz@upm.es)
- Dr. Jorge Dueñas (jorge.duenas.lerin@upm.es)
- Dr. Felix Fuentes (felix.fuentes@upm.es)
- Dr. Ángel González-Prieto (angelgonzalezprieto@ucm.es)
- Dr. Guillermo Iglesias (guillermo.iglesias@upm.es)
- Dr. Raúl Lara-Cabrera (raul.lara@upm.es)
- Dr. Rodrigo Mariño (rodrigo.marino@upm.es)
- Dr. Edgar Talavera (e.talavera@upm.es)
Students
- Víctor Ramos Osuna
- Diego Pérez-López
Recent publications (last 5 years)
2025
- Pérez-López D., Bojorque, R., Dueñas-Lerín, J., & Ortega, F. Deep Learning based Stacking for Recommender Systems, 10th International Conference on Information and Communication Technology for Recommender Systems (ICTIS 2025) (New York, USA).
- Dueñas-Lerín, J., Lara-Cabrera, R., Ortega, F., & Bobadilla, J. (2025). Deep neural aggregation for recommending items to group of users, Applied Soft Computing 175, 113059.
- Iglesias, G., Zamorano, M., & Sarro, F. (2025). Search-Based Negative Prompt Optimisation for Text-to-Image Generation. International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar), pp. 94-110.
2024
- Mayor, J., López-Fernández, D., Lara-Cabrera, R., & Ortega, F. (2024). Virtual Reality Presence in Partially non-Euclidean Environments, PRESENCE-Virtual and Augmented Reality, 1-14.
- Mazón, M. J. C., García, R. M., García, E. A., del Castillo, M. H. G., & Iglesias, G. (2024). Binary Classification Optimisation with AI-Generated Data. IFIP International Conference on Testing Software and Systems (pp. 210-216).
- González‐Miguéns, R., Cano, E., García‐Gallo Pinto, M., Peña, P. G., Rincón‐Barrado, M., Iglesias, G., … & Lara, E. (2024). The voice of the little giants: Arcellinida testate amoebae in environmental DNA‐based bioindication, from taxonomy free to haplotypic level. Molecular Ecology Resources, e13999.
- Iglesias, G., Talavera, E., Troya, J., Díaz-Álvarez, A., & García-Remesal, M. (2024). Artificial intelligence model for tumoral clinical decision support systems. Computer Methods and Programs in Biomedicine, 253, 108228.
- Pérez-López, D., Ortega, F., González-Prieto, A., Dueñas-Lerín, J. (2024). Incorporating Recklessness to Collaborative Filtering based Recommender Systems, Information Sciences 679.
2023
- Gutierrez-Cabello, G. S., Talavera, E., Iglesias, G., Clavijo, M., & Jiménez, F. (2023). A Novel Method to Generate Auto-Labeled Datasets for 3D Vehicle Identification Using a New Contrast Model. Applied Sciences, 13(7), 4334.
- Iglesias, G., Talavera, E., & Díaz-Álvarez, A. (2023). A survey on GANs for computer vision: Recent research, analysis and taxonomy. Computer Science Review, 48, 100553.
- Iglesias, G., Talavera, E., González-Prieto, Á., Mozo, A., & Gómez-Canaval, S. (2023). Data augmentation techniques in time series domain: a survey and taxonomy. Neural Computing and Applications, 35(14), 10123-10145.
- Dueñas-Lerín, J., Lara-Cabrera, R., Ortega, F., & Bobadilla, J. (2023). Neural group recommendation based on a probabilistic semantic aggregation, Neural Computing and Applications, In press.
2022
- Bobadilla, J., Ortega, F., González-Prieto, A., & Gutierrez, A. (2022). Deep Variational Models for Collaborative Filtering-based Recommender Systems, Neural Computing and Applications, 1-15.
- A. González, F. Ortega, D. Pérez-López, & S. Alonso (2022). Bias and unfairness of collaborative filtering based recommender systems in MovieLens dataset, IEEE Access, 10, 68429-68439.
- Bobadilla, J., Dueñas, J., Gutiérrez, A., & Ortega, F. (2022). Deep Variational Embedding Representation on Neural Collaborative Filtering Recommender Systems, Applied Sciences-Basel 12 (9), 4168.
- Lara-Cabrera, R., González, A., Ortega, F., & González-Prieto, A. (2022). Dirichlet Matrix Factorization: A Reliable Classification-Based Recommender System, Applied Sciences-Basel 12 (3), 1223.
- Bobadilla, J., González-Prieto, Á., Ortega, F., & Lara-Cabrera, R. (2022). Deep Learning Approach to Obtain Collaborative Filtering Neighborhoods, Neural Computing and Applications 34, In Press.
2021
- López-Fernández, D., Gordillo, A., Ortega, F., Yague, A., & Tovar, E. (2021). LEGO® Serious Play in Software Engineering Education, IEEE Access 9, 103120-103131.
- Ortega, F., Lara-Cabrera, R., González-Prieto, A., & Bobadilla, J. (2021). Providing Reliability in Recommender Systems through Bernoulli Matrix Factorization, Information Sciences 553, 110-128.
- Ortega, F., Mayor, J., López-Fernández, D., & Lara-Cabrera, R. (2021). CF4J 2.0: Adapting Collaborative Filtering for Java to New Challenges of Collaborative Filtering based Recommender Systems, Knowledge-Based Systems 215, 106629.
- Bobadilla, J., Lara-Cabrera, R., González-Prieto, Á., & Ortega, F. (2021). DeepFair: Deep Learning for Improving Fairness in Recommender Systems, International Journal of Interactive Multimedia and Artificial Intelligence 6, 86-94.
- Bobadilla, J., González-Prieto, Á., Ortega, F., & Lara-Cabrera, R. (2021). Deep Learning feature selection to unhide demographic recommender systems factors, Neural Computing and Applications 33 (12), 7291-7308.
- Pajuelo-Holgera, F., Gómez-Pulido, J.A., & Ortega, F. (2020). Recommender Systems for Sensor-based Ambient Control in Academic Facilities, Engineering Applications of Artificial Intelligence Article 96, 103993.
Active research projects
- ALENTAR-J-CM: Aplicación de modelos del LENguaje a gran escala para la prevención sociosaniTAria de problemas de salud mental y Riesgo de suicidio en Jóvenes (TEC-2024/COM-224). Project funded by Comunidad de Madrid, Consejería de Educación, Ciencia y Universidades. From jan 2025 to dec 2028. Principal Investigator: Raúl Lara-Cabrera.
Thesis
- D. Guillermo Iglesias Hernández. Advanced Deep Learning Models for Precise Medical Image Analysis and Diagnosis. Doctorado en Ciencias y Tecnologías de la Computación para Smart Cities (Universidad Politécnica de Madrid). Supervisors: D. Edgar Talavera Muñoz. Febrero 2025.
- D. Jorge Dueñas Lerín. Recomendación a grupos de usuarios usando técnicas de aprendizaje profundo. Doctorado en Ciencias y Tecnologías de la Computación para Smart Cities (Universidad Politécnica de Madrid). Supervisors: D. Raúl Lara Cabrera & Dr. Fernando Ortega. April 2024.
- D. Francisco Pajuelo Holguera. Sistemas de recomendación basados en filtrado colaborativo: aceleración mediante computación reconfigurable y aplicaciones predictivas sensoriales. Doctorado en Tecnología Aeroespacial: Ingenierías Electromagnética, Electrónica, Informática y Mecánica (Universidad de Extremadura). Supervisors: Dr. Juan Antonio Gómez-Pulido & Dr. Fernando Ortega. July 2021.
- D. Remigio Hurtado Ortiz. Recomendación a grupos de usuarios usando el concepto de singularidades. Doctorado en Ciencias y Tecnologías de la Computación para Smart Cities (Universidad Politécnica de Madrid). Supervisors: Dr. Jesús Bobadilla & Dr. Fernando Ortega. February 2020.
- D. Rodolfo Bojorque Chasi. Clustering de sistemas de recomendación mediante técnicas de factorización matricial. Doctorado en Ciencias y Tecnologías de la Computación para Smart Cities (Universidad Politécnica de Madrid). Supervisors: Dr. Jesús Bobadilla & Dr. Fernando Ortega. February 2020.
Research resources
- Collaborative Filtering for Java (CF4J): an object-oriented Java framework designed for the trial and error process for Collaborative Filtering research.
- make_spirals: a Python module to generate a synthetic data set composed of interlaced Archimedean spirals.
- You can also visit our organization in GitHub.