Find the right data for You!

Get knowledge without exiting Cross-CPP

It may be complicated to get access to huge amount of data. Yet, is this the only challenge? Surely not. As it is well-known in the machine learning community, having data is not tantamount to having knowledge. The Analytics Toolbox simplifies the extraction of the latter, by providing a set of libraries and modules designed to satisfy most data-related needs, and based on the most recent concepts and algorithms developed by the scientific community. It is buttressed by a modular structure, in which new analytics services can be added to fulfil new requirements; and in which multiple algorithms can be chained together, to give answer to even more complex questions.

But how will this Analytics Toolbox help you?

  • By enabling fast prototyping. No data to download, no library to develop and deploy in-house. The Analytics Toolbox enables performing a first feasibility evaluation of a new business idea at essentially no cost.

  • By unleashing the power of advanced algorithms. The Toolbox includes modules not easily available in other all-purpose analytics solutions, and specifically designed with CPP data in mind. These span from the analysis of thousands of trajectories, to the representation of network relationships. Again, no in-house development is required: the Toolbox includes everything is needed for a first evaluation.

  • By minimising overheads. Filter your data prior to download, for instance through averaging, clustering, or through event-driven triggers. Only download what you need, and when you need it.

Which analyses can be executed?


  • Basic statistics and data aggregation: from statistical metrics of location and dispersion, to analysis of distributions and entropies.


  • Time series analyses, including the detection of drifts, or sudden changes, through the application of statistical and data mining models.


  • Trajectory analyses. From the processing of individual trajectories, including interpolations and error detections; to multivariate scenarios, as in the detection of clusters of similar trajectories - see the image for an example.


  • Network analyses, for understanding the structures created by interacting elements.

Read more:


This project has received funding from the European Union’s Horizon 2020 research and innovation programm under grant agreement No. 780167. This website reflects the views only of the Consortium, and the Commission cannot be held responsible for any use which may be made of the information contained herein.

  • Schwarz LinkedIn Icon
  • Schwarz Twitter Icon