AI consultant in Arnhem
For sports federations, clubs and talent programmes around Papendal. We build tools that help you track and compare young athletes, like those we built for Van Amersfoort Racing.
Together with Van Amersfoort Racing, we developed a tool to track and compare young racing drivers
“[…] We are very happy with our collaboration and confident this will be a very powerful tool in our search for talented young drivers.” Francisco Freitas, Sporting Affairs Business Development - Van Amersfoort Racing (VAR)
What does all that training data tell you about a single athlete?
At Papendal, the TeamNL Sport Science Centre puts measurement data straight to use in training. At clubs and regional talent programmes, GPS, heart rate and test data are often still spread across separate apps and spreadsheets. Bring them together and you can see how a week of training affected each athlete.
Coaches review training, scouts track development
One overview per athlete
GPS, heart rate, jump sensors, test results and training apps linked by name and date, so the staff can see a week of training in one view.
Feedback during training
For DutchSail, we developed a real-time dashboard that lets coaches track their sailors’ performance in the AC-40 simulator.
Track and compare talent
For Van Amersfoort Racing, we developed a tool in Python and Dash that lets the team track and compare young drivers.
Keeps working beyond the season
New sensors, a new generation of athletes, a different coach: through management and continuous improvement, we keep integrations and models up to date as things change.
The coach’s question comes before the sensor
-
Define one decision
For example, who moves up to a higher-level squad, or how much training load an athlete can handle after an injury.
-
Look back at a season
Using data from a previous season, we assess whether the measurements would have provided a stronger basis for that decision.
-
Build it into the training week
If it works, the overview becomes part of the routine for staff and athletes, with someone responsible for it and ongoing management.
Could our federation, club or talent development programme benefit from this?
A good fit if
You train or select athletes with a regular team of staff, you already collect measurements from GPS, heart rate, testing or a simulator, and a recurring decision—such as training load or athlete progression—could be better informed.
Not a good fit if
Your measurements cannot yet be compared across a season, or the decision relies mainly on an experienced coach’s judgement. In that case, start with regular testing and a simple dashboard.
What determines the scope
The number of athletes and measurement systems; whether sensor and app suppliers offer an export or integration; whether you want to review data in real time or after training; and whether your team or ours will manage the platform.
Who can see an athlete’s data?
Heart rate, sleep and injuries can quickly count as health data. Agree in advance what the coach, scout and medical staff can see. We set up those access permissions in the platform.
Real-time feedback, talent selection or training load: where can your data deliver value first?
Real-time feedback
Choose this if coaches want to make adjustments during a session and measurements are already coming in digitally, as they do from the DutchSail sailing simulator.
Talent selection
Choose this if you select talent every year and have test results from several cohorts. Our advice: account for birth month, or the model will learn to replicate past selection decisions.
Training load
Choose this if injuries and excessive training load cost you the most, and you already record GPS, heart rate or RPE data for each training session. Start with an overview in Power BI.
Our sports case studies take us to the track and onto the water
Data Science Lab has been around since 2016 and is a Databricks and Microsoft partner. We worked with Python, Dash, Kafka and Grafana for Van Amersfoort Racing and DutchSail. Based in Amsterdam, we can meet at your place, ours or online.

The conversation starts with a decision your staff needs to make
Stef Stoelwinder
Business DevelopmentStef is your point of contact. In our first conversation, we’ll discuss which decision your staff wants to support with evidence, what measurements are already available and who will work with the results.
E-mail info@datasciencelab.nl
Phone +31 (0)20 3636 724
Which athletes or squad selections is our staff unsure about right now?
Briefly describe which athletes, measurements or selections you mean. You’ll receive a reply by email, or we’ll arrange an initial conversation at your place, at ours or online.
Message sent
Thanks for your message. We’ll be in touch as soon as possible.
Frequently asked questions
No. They are our case studies in sport, and we mention them here as examples of what we do with performance and talent data. DutchSail has its team base in Scheveningen. We have not published a case study with a club, federation or talent programme in Arnhem.
Our office is on Westerdoksdijk in Amsterdam. We can meet at your premises, at ours or online. You can read about our work in this sector on the data and AI for the sports sector page.
At Papendal, on the outskirts of Arnhem, the TeamNL Sport Science Centre supports sports federations and elite sports programmes. It measures strength, technique, endurance and recovery, among other things, and uses testing and measurement equipment to provide immediate feedback during training. NOC*NSF has its office there, and federations including Atletiekunie and KNWU are based there.
We do not build measurement equipment. We can, however, connect test results to daily data from GPS, heart rate monitors and training apps, so staff can also see what happens between tests. That requires data engineering and an agreement on who manages the data: the federation, the club or the programme.
By testing for that bias from the start. Children born in the same calendar year are treated as the same age, but can be almost a year apart. An analysis of PSV’s youth academy in Demos, the NIDI bulletin, showed an overrepresentation of relatively older players in 2018: the relative age effect. A model trained on past selections will reproduce that effect.
So compare athletes with peers born in the same part of the year, and look at their development across multiple assessments rather than a single test. The coach’s judgement remains decisive; the model helps identify athletes they might otherwise overlook. You can read how we advise on fair and transparent models under Responsible AI.
Only under strict conditions. The Dutch Data Protection Authority classifies data on how much someone exercises, sleeps and weighs as health data. This is a special category of personal data: processing it is prohibited unless a GDPR exception applies and you have a lawful basis. According to the authority, consent from an employee in a dependent position can never be freely given; an athlete may also be dependent on the person asking for consent.
If you rely on explicit consent and the young athlete is under 16, a parent or guardian must give it; from the age of 12, the child can withdraw that consent themselves. Use data governance to define what coaches, scouts and medical staff can see. Your legal counsel or data protection officer should assess how the law applies to your situation.
Measurements arrive as a continuous stream and are processed while the session is under way. For DutchSail, we developed a real-time dashboard for the AC-40 simulator, using training data such as steering behaviour and sail settings. In that case study, we used Python, Kafka—a platform for such data streams—and Grafana, software for dashboards, among other tools.
Real-time processing is worthwhile only if the coach can intervene during the session. If staff review the data afterwards, processing it after training is simpler to build and manage. The source is often the hardest part: not every sensor or simulator makes its data available through an interface.
“The experts at Data Science Lab helped us streamline our dataflow by looking at the broader picture as well as solving the difficult IT issues we had […]” Dirk-Jan Korpershoek, DutchSail
Usually two types. External load is what an athlete does, such as distance covered, sprints and jumps recorded by GPS and sensors. Internal load is how that effort affects the athlete, measured through heart rate and session-RPE: how hard the athlete says the session felt afterwards. According to TeamNL, team sports were already using GPS systems, heart rate monitors and jump sensors in training in 2018.
Add injury history from the medical staff, and you can see how load and symptoms relate for each athlete. One pitfall: if the club changes GPS provider, figures from before and after the switch often cannot be compared directly. Record the change before you train a model.
In Gelderland’s Sport programme, Topsport Gelderland and Gelderse Sport Federatie work together on Sportief Groot Worden. The initiative conducts motor skills tests, maps sporting preferences and collects data on primary school children’s physical activity and sports participation. This produces physical activity profiles that municipalities can use as a basis for activities in neighbourhoods and local communities.
Such data tells you a lot at neighbourhood or school level, but only becomes meaningful for an individual child after multiple assessments. In 2016, before the GDPR came into force, the Dutch Data Protection Authority classified data on pupils’ motor skills as health data in school-based health projects. A neighbourhood-level Power BI dashboard is therefore often a more sensible first step than a model for each child.
Which route is right for your sports data?
- AI consultancyOur nationwide approach to deciding which decision to support with an AI application first.
- Data & AI for the sports sectorWhat we do for clubs, federations and teams that want to track performance and development.
- Data scienceHow we build predictive models, from initial testing on historical data through to management.