University of Amsterdam Publishes Open-Source Algorithm to Help Regulators Assess Online Casino Player Risk
TL;DR — University of Amsterdam researchers released a free open-source algorithm that calculates player risk scores from betting patterns, timing and streaks. Trained on all player data from 13 Dutch online casinos across two years, the tool supports the Kansspelautoriteit in assessing operator duty of care. The model is publicly available to regulators globally.
SCCG Take — Regulators gain an independent benchmark to test commercial risk tools, which may tighten compliance expectations for operators in multiple jurisdictions.
Researchers from the University of Amsterdam have released a free open-source machine learning algorithm. The tool estimates risky gambling behaviour among online casino players using actual gaming data. It provides regulators with an independent method to detect problems early and review operators’ duty of care compliance.
The algorithm examines betting patterns such as amounts wagered and frequency, session timing including consecutive nights of play, and player responses to win and loss streaks. It produces a risk score across all forms of online gambling. The Kansspelautoriteit intends to apply the model to compare its calculations against those of providers.
The researchers highlighted that 60 per cent of online casino revenue comes from excessive gamblers who play frequently with significant financial, psychological and social effects. They cited recent figures from the French regulator. Dutch casinos hold a legal duty of care yet also control the most detailed customer data.
Charles de Leau, a PhD candidate, developed the model with University of Amsterdam professors Reinout Wiers (Psychology) and Johan Bollen (Computer Science). De Leau drew from personal experience of gambling addiction among family and friends. The project received funding from the Kansspelautoriteit’s Addiction Prevention Fund through ZonMw.
Training on Unprecedented Scale of Player Data
The model was trained on all bets made by all players at 13 Dutch online casinos over a two-year period from July 30, 2023, to July 30, 2025. Dutch legislation requires casinos to supply this data for independent research. De Leau is the first researcher to use the provision.
De Leau stated: “The fact that we were able to analyse all bets from 13 different casinos over two years has never been done before by independent researchers.” He added: “With this massive amount of data, which is normally used by casinos themselves for marketing purposes, we can see for the first time on such a scale which patterns in gambling behaviour often precede serious problems.”
Collaboration with Spanish Authorities
Development occurred in close collaboration with the Spanish gambling regulator, the DGOJ, which is building its own model. The algorithm, code and methodology are now publicly available on the Kansspelautoriteit website. This allows regulators worldwide to avoid reliance on the closed systems of casinos themselves.
According to reporting by Focus Gaming News, the researchers described the tool as a transparent frame of reference free from commercial interests.
Reporting: Focus Gaming News
Generated by SCCG’s automated editorial system from published source reporting. SCCG Management holds editorial responsibility.
The first independent, public benchmark for operator risk tools — raising the compliance bar for duty of care globally.
We've watched regulators struggle to audit black-box risk tools operators build in-house. This open-source model, trained on two years of real data from 13 Dutch casinos, gives Kansspelautoriteit and others a yardstick to measure compliance. That shifts power — and compliance expectations — fast across Europe and beyond.
- University of Amsterdam trained algorithm on all bets from 13 Dutch casinos over two years
- Kansspelautoriteit will compare operator risk models against this independent benchmark
- Model is open-source and available to regulators worldwide
SCCG angle: SCCG connects operators to the compliance tech and responsible gaming partners who can align internal risk models with emerging regulatory benchmarks. We help clients navigate Dutch, Spanish and emerging European standards before audits tighten.
Gaming, betting and prediction markets — the desk’s read, every weekday.
Subscribe →