Gambling regulators can use the free tool to detect risky gambling behaviour and assess online casino operators’ duty of care compliance.
The Netherlands.- Researchers from the University of Amsterdam (UvA) have released a free open-source algorithm designed to estimate risky behaviour of online casino players based on their actual gaming behaviour. The tool, which will be used by the Dutch gambling regulator Kansspelautoriteit (KSA), is intended to provide regulators with an independent, transparent instrument to detect risky gambling behaviour early and better assess whether online gambling companies are fulfilling their duties of care.
The machine learning algorithm looks at the actual behaviour of players, for example betting patterns (how much and how often someone bets), frequency and times (for example, playing at night for days in a row) and loss and win streaks and how players react to them. Based on the patterns, the model calculates a risk score. All forms of online gambling have been included in the model, which the KSA intends to use to calculate risk scores and compare them, for example, with the risk scores used by providers.
The researchers stressed that unlike commercial providers of such tools, they are making their tools available for free and open source. The model, code and methodology have been made publicly accessible on the KSA website to allow other parties to make use of it to avoid the need to rely on the d systems of casinos themselves.
“Since the legalisation of online gambling in the Netherlands, the market has grown explosively. Through apps, games, and social media, an online casino is always within reach. Recent figures from the French regulator show that around 60 per cent of online casino revenue comes from excessive gamblers: people who gamble frequently and for extended periods, with major financial, psychological, and social consequences,” the researchers said.
“Dutch casinos have a legal duty of care towards their players. At the same time, they possess the most detailed data of their customers – data that can be used to bind players to them. Using that same data, tools could be developed that attempt to predict when a player is at risk of becoming addicted. Virtually all existing analytical tools for this purpose were developed by or in cooperation with the casinos. With a public and independent model, regulators worldwide now have their own transparent frame of reference at their disposal, free from commercial interests.”
The tool was developed by PhD candidate Charles de Leau with UvA professors Reinout Wiers (Psychology) and Johan Bollen (Computer Science). De Leau says he had personal experience of the impact of gambling addiction on family and friends. That inspired him to pitch the concept to ZonMw, which subsequently funded the project from the KSA’s Addiction Prevention Fund.
The model was trained on, among other things, all bets made by all players at 13 Dutch online casinos over a two-year period (July 30, 2023, to July 30, 2025). This data was obtained through a legal provision that requires Dutch casino operators to make their user data available for independent research. De Leau is the first and, so far, the only one to have ever made use of this provision.
“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,” said De Leau. “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.
He added: “This is a very different way of looking at player protection, and that will be quite a shift for many parties. In my opinion, however, it is incredibly important in this rapidly growing market that we are given more opportunities to protect players.”
The development of the model involved collaboration with the Spanish gambling regulator, the DGOJ, which is also developing an AI-driven gambling surveillance model itself.
Este conteúdo foi curado e adaptado a partir da publicação original de Focus Gaming News.