Borja Sanz Urquijo

Borja Sanz Urquijo

Assistant Professor of Programing and A.I.

University of Deusto


Dr. Borja Sanz Urquijo (male) is asociate proffesor of the Faculty of Engineering of the University of Deusto, and was the Head Researcher for DeustoTech Computing from 2015 to 2018. He received his PhD from the PhD program in Information Systems with full marks cum laude in 2012 in the topic of malware detection in Android mobile devices. My research interests are artificial intelligence and the impact it has on society. I seek to advance in the creation of more efficient, efficient and fair machine learning models.


  • Artificial Intelligence
  • Computational Linguistics
  • Information Retrieval
  • Fariness, Accountability, Transparency, Ethics


  • PhD in Artificial Intelligence, 2012

    University of Deusto

  • MEng in Information Security, 2011

    University of Deusto

  • Computer Science Engineering, 2007

    University of Deusto




Machine Learning






Assistant Proffesor

University of Deusto

Jan 2019 – Present Bilbao

Responsibilities include:

  • Teaching
  • Research activities
  • Management

Associate Researcher


Jan 2017 – Dec 2018 Bilbao
Research activities.



Sep 2008 – Dec 2017 Bilbao
Research activities.

Recent Posts


Here we have a selection of porojects where I have been working in the last years.



In BEHAVE, we are collaborating with Dr. Ana Estevez and Dr. Paula Jauregui, from the Faculty of Psycology and Education of the University of Deusto, and with RETABet Group in order to try to identify gambling behaviours in their users.


The project HORUS gathers three of the most outstanding companies in Spain’s steel sector, members of the Spanish technological steel platform, PLATEA (Sidenor, Acerinox and ArcelorMittal), which share the general objective of developing innovative technology solutions aiming at improving productivity, the efficiency of energy resources as well as the sustainability of processes.

PRODEC: Industrial PROduct Configuration DECission Support System

In collaboration with Semantic Systems, we are working in the project PRODEC. The objective of the PRODEC project is to investigate and develop a system that speeds up product configuration times (oriented to users without high qualification), based on the experience of previous configurations.

Proof of Concept: Mercedes Painting process

We collaborate with Mercedes Benz in the Vitoria-Gazteiz factory to help them to improve the painting process using advance data analitycs and machine learning algorithms.


The DANTE (Detecting and analysing terrorist-related online contents and financing activities) project aims to deliver more effective, efficient, automated data mining and analytics solutions and an integrated system to detect, retrieve, collect and analyse huge amount of heterogeneous and complex multimedia and multi-language terrorist-related contents, from both the Surface and the Deep Web, including Dark nets.


Gender Equality Actions in Research Institutions to traNsform Gender ROLES (GEARING-Roles) is a strong multidisciplinary consortium of 10 European academic and non-academic partners that will design, implement, and evaluate 6 Gender Equality Plans (GEPs) following the steps described in the GEAR tool (define, plan, act and check) with the firm objective of challenging and transforming gender roles and identities linked to professional careers, and work towards real institutional change.

Recent & Upcoming Talks

Recent Publications

Territorial innovation models: to be or not to be, that’s the question

Industrial agglomerations are key in explaining the development paths followed by territories, particularly at sub-national levels. …

Hic sunt dracones: derechos humanos y big data: análisis de una colaboración inexplorada

Esta obra aglutina contribuciones de un conjunto de expertos de primer nivel que disertan sobre …

How IoT and computer vision could improve the casting quality

In recent years, Internet of Things has being used in several fields of modern life. The possibility of having an interconnection …

Surface Defect Modelling Using Co-occurrence Matrix and Fast Fourier Transformation

An unsupervised approach to online noisy-neighbor detection in cloud data centers