Products

Data Management

---

We harvest unstructured data from data bases, files, homepages and data catalogues to homogenize it. Well defined dimensions, variables and attributes allow for advanced processing, visualization and increase the data reusability. We know about the importance of metadata, controlled vocabularies and data transformations.

Full Stack Development

---

Processing in the backend and visualization in the frontend. Knowledge on the full technology stack enables us to choose the path of least resistance from development to deployment. On linux system level, in python or in javascript: "Simplicity is everything."

Machine Learning

---

A vast amount of advanced statistical methods are embraced by the term machine learning. Choose features, create models and validate them. We are open for new methods and have in depth knowledge on non-linear tree-based machine learning methods, such as random forests and gradient boosted trees.

Consulting

---

Data driven projects are doomed to failure if goals are not defined beforehand. We offer support, evaluating your data and defining your goals in order to choose the most promising method. Our knowledge in the open source domain contributes greatly towards the saving of labour.