Data Science

The Data Science team at CentERdata works on techniques and applications related to massive amounts of (complex) data from various sources, so-called big data. We employ machine and deep learning, data and text mining, and visualization techniques. Expertise in econometrics, data engineering, cognitive science, artificial intelligence, and software development is combined in this team. By doing so, we are able to derive new insights and create (societal) value from all sorts of data, such as sensor data, social media data, or data scraped from the Internet.

Among other things, we implement and work with:

  • big data infrastructures
  • powerful calculation clusters
  • visualization of complex data
  • data mining and text mining
  • signal analysis, sensor data, internet of things
  • analysis of natural language
  • cluster and classification techniques
  • machine learning and deep learning

Primarily, we work with open source systems, script languages, visualization packages, plug ins, and online analysis tools. Our objectives include deep pattern recognition, predictions using various algorithms, decision-making process modelling, complex data visualizations, and facilitating research on the interface with data science.

CentERdata collaborates with the Data Science Center Tilburg (DSC/t) and the Jheronimus Academy of Data Science (JADS) in Den Bosch. Two recent projects are a Multiple Choice Question generator based on machine learning and natural language processing and an analysis and visualization of metadata of peer-reviewed publications that are related to the term “big data”.