Machine learning to help predict online gambling addiction
Mon 26 Oct 2015
A new system designed to help users control their online gambling, provides an ‘early warning’ notification to gamblers who show signs of addiction.
The software, developed by teams at City University London and gaming analytics start-up BetBuddy, traces users’ gambling habits and points to potential signs of risk by comparing data collected from previous addicts who have since asked to be blocked from online game sites.
The underpinning computer models have been developed according to the latest findings from psychological pathway studies into gambling addictions. The research was funded by Innovate UK, under its Data Exploration programme. The system is also backed by the RCUK Digital Economy Theme, the Engineering and Physical Sciences Research Council (EPSRC), the Economic and Social Research Council (ESRC) and the Defence Science and Technology Laboratory (DSTL).
“All UK gambling providers are legally obliged to offer customers a self-exclusion option,” said City University Professor Dr Artur Garcez. “Our aim has been to help BetBuddy test and refine their system so that it gives providers an effective way of predicting at an earlier stage self-exclusion as well as other signals or events that indicate harm in gambling. This enables customers to use online gambling platforms more securely and responsibly,” he continued.
Garcez explained that a machine learning technique called ‘random forests’ was applied to the dataset, where it could achieve 87% accuracy in predicting gaming patterns which were likely to grow into a serious problem.
The system further allows providers to decide whether or not to send users marketing materials, or whether to suggest self-exclusion to the player.
Online betting and gambling is a huge global growth sector, with EU revenue alone expected to reach over €13bn this year. The industry also contributes to the growing number of problem gamblers, of which there are an estimated 593,000 in the UK.
EPSRC CEO Professor Philip Nelson commented: “This project is an example of how artificial intelligence and machine learning methods can be used to address an important social problem.”