- Professor Artur d'Avila Garcez (Principal Investigator)
- Dr Tillman Weyde (Co-Investigator)
Around 47 per cent of people in Britain have gambled in some way over the last four weeks and the rapid growth of online gambling has seen a rise in vulnerable gamblers.
A partnership between City, University of London’s Research Centre for Machine Learning and software analytics firm, BetBuddy, developed an ‘early warning’ system which has enabled operators to identify early signs of user gambling problems.
The research has also allowed the gambling industry to meet more increasingly stringent regulations and has evolved to explore how big data might help prevent money-laundering within the gambling industry.
What did we explore and how?
The partnership with BetBuddy, established by Professor Artur d'Avila Garcez and Dr Tillman Weyde, from City’s Department of Computer Science, uses a machine learning model to predict early signs of gambling related problems.
The system will identify whether a player’s gambling patterns show signs of risk and start to match those of previous players who asked online gambling sites to block them for a fixed period – an option known as ‘self-exclusion’.
The research team discovered that by harnessing a machine learning method known as ‘random forests’ and applying it to a real-world online gambling dataset, the system could achieve an impressive 87 per cent accuracy in predicting playing patterns which were likely to evolve in an unhealthy direction.
Benefits and influence of this research
The research conducted by the City academics and BetBuddy has featured in both national and international press. In 2013, work from the collaboration was cited as a positive example of betting control during a parliamentary debate of the Gambling Bill.
The software has gone onto win multiple industry awards, partner with leading betting companies and contribute to the safety of online gamblers.
In 2017, BetBuddy was acquired by Playtech – the world’s largest provider of online gambling and sports betting software. Playtech integrated BetBuddy into their nine platforms meaning the software was able to reach 3 million registered gamblers.
In 2020, Playtech’s BetBuddy team was selected to lead the UK Gambling Commission collaboration group working on developing the first Industry Code for Product Design.
Recently, the collaboration has also combined with online gambling operator, Kindred, to explore the use of artificial intelligence in strengthening anti-money laundering decision-processes. The partnership has since produced an industry whitepaper of recommendations, as well as presenting early analytical research at the 2018 European Association for the Study of Gambling (EASG) conference.
Details of this research
Research status: Completed
Topic: computer science, gambling, technology
Industry/sector: Gambling, Computing, Artificial Intelligence
School of Science & Technology