AI / DATA SCIENCE / RESEARCH

CARDAAI, built to matter.

Creating things that work, teaching people how to build them, and making AI easier to reason about.

Charles, the person behind Carda, smiling in a light suit against a blue background.

build decide understand speak research

Hi, I’m Charles. I build, teach & research AI.

One curious mind. Five ways to work together.

01 Creating AI solutions. 02 Workshops for builders 03 AI Strategy masterclasses 04 Inspirational talks 05 Research

Selected work / 04 projects

Projects that
make AI useful

FARO: gambling activity data flows through a machine learning model to produce a risk score. The activity chart is illustrative.

FARO[1/4]

For this project, I ...

quit my job after five years as Principal Data Scientist for Shopping & Advertising at bol, the Netherlands’ largest e-commerce company,
pitched to ZonMw, which got the idea funded,
collected two years of all customer data from 13 licensees (hasn’t been done before),
trained a machine learning model that gives back a risk score.

On 18 Aug 2026, the resulting open-source tool was published by the Dutch Gambling Authority. It was featured on NOS, Trouw, BNR, multiple international media and discussed in Dutch parliament.

NOS coverage ↗ Project link ↗

KNOWNWELLJAN 2024 - JAN 2026 · 2 YRS 1 MO

Commercial intelligence for better decisions.

I was given the opportunity to join a US startup innovating at the cutting edge of AI. Knownwell creates insights into client portfolios and business health, combining AI with traditional machine learning so professional-services leaders can protect revenue, reduce churn and grow accounts with confidence.

For this project, I worked on turning fragmented signals from client communications and business systems into a clearer, more actionable view of commercial reality.

The challenge was to get reliable results, provide instructions that were easy to follow, and make sure the AI worked on the right thing. The product needed to surface the signals that matter without asking teams to manually score clients or babysit another dashboard.

Knownwell ↗

SPINE[3/4]

I was asked to build the architecture of a Demand-Side Platform (DSP) in 2023 by Frans Vermeulen, who I thank for then recommending me for promotion into a manager role. I only wanted to do it if I was given the guarantee to do 50% coding on the side, which I had to request from the CTO at the time, which was Jurrie van Rooijen.

I started with two of my direct reports. After 1 year, 8 teams were working on this solution as its profit was over 100M EUR/year, of which 8M per year cost saving due to building in house solutions. It was a very cool problem, as it combined search solutions (NLP), recommender systems and auctioning logic. And it needed to be very fast.

After two years of management experience, I decided I was missing the coding too much, and I transferred into the role of Data Science Craft Lead for Shopping and Advertising, the largest domain of bol.

OSCAR[4/4]

During a two-day hackathon, I created a natural language microservice (‘Oscar’) which evaluates comments of returned products, generating 400.000 EUR/year.

I like this project because it was super fun to create, and it signifies the power of being able to completely deploy a service on your own. Things don't always need to be complicated if you have the right tools and surroundings.

Not the most life-changing tool, but a fun example of how a hands-on innovation can be made with relative ease.

Formats

Workshops &
Masterclasses

Three ways to move from idea → decision → understanding.

01BUILD

Turn an idea into something that actually works.

Hands-on sessions for people who want to move beyond talking about AI. Start with a real problem, build something tangible and learn an approach you can reuse afterwards.

⌁

AI/DS Prototype

From a problem, how do we get to a solution?

↯

AI Sprints

How can we collaborate with AI as a team?

02DECIDE

Make better AI decisions without having to become an AI engineer.

Decision tools for finding and shaping the problems worth solving.

⊞

Creating an AI Impact Evaluation Chart

How can we identify the right problems to work on?

◇

AI Prototype Epic

How can we make sure that AI innovation is happening?

03UNDERSTAND

Understand what's real, what's hype and what is coming next.

A clearer view of what current AI can and cannot do.

≠

What AI can and cannot do.

A fun workshop where we deep dive into the limitations of LLM's

→

What is next?

A sparring session where we challenge ourselves

Not sure which format fits?

Tell me what you are trying to achieve. I'll suggest the format that makes most sense — or combine several into one session.

Start a conversation ↗

On stage

Inspirational
talks

I like talking about AI!

01 PYCON NL 2026 Talk ↗ 02 GGZ-Congres Kennis in Beweging Conference ↗ 03 Digitalisering: Make it real Conference ↗ 04 NAGS CONFERENCE 2026 Conference ↗

05 / Research

Research that
helps decide.

From policy evaluation and public-sector data to international gambling research, I work where evidence needs to become useful.

Since 2013, I have written and led policy evaluations, including four years in central government across AI, cybersecurity and online gambling. I have advised policymakers, built indicators for annual budgets and reports, and initiated data-driven research with partners in the field.

2013: research and policy evaluations
4 years: central government experience
3.5m: students in a national forecast
€2.5m: ZonMw budget for gambling research WP1

Selected researchPUBLIC / APPLIED

A body of work across policy, data and gambling.

Public policy & evaluation

Developing the Annual National Forecast of Public School Enrollment, predicting the learning journeys of 3.5 million students through time-series modelling. I also helped policymakers establish reliable KPIs for annual budgets, reports and dashboards, and supervised progressive data-driven research with external partners.

Government, security & society

My policy work covered cybersecurity, including a seven-month research project on splitting government networks and partnerships with multinational companies for the Alert Online awareness campaign. Other assignments included communication with the Inspectorate of Education, research into radicalisation in schools, and projects connecting prisons with mental-health institutions.

International collaboration

In Australia, I worked with Sally Gainsbury's team at the University of Sydney on gambling research and co-authored a published paper. I also chaired a group of policy advisers investigating how gambling websites communicate with customers.

FARO: from evidence to action

For my recent PhD research with Reinout Wiers at the University of Amsterdam, I secured ZonMw funding and studied the legislation and responsible-gambling context behind the work. The result is FARO: an open-source tool that turns behavioural data into an interpretable risk score for earlier, more targeted support.

Part of a national research consortium

I am part of the consortiums investigating gambling in WP1. The ZonMw round has €8 million available in total: €2.5 million for WP1, €2.5 million for WP2 and €3 million for WP3, with cofinancing required.

Read the NOS coverage

Contact

charles@carda.nl