New software predicts gambling addiction at an early stage

TAGs: BetBuddy, Europe, problem gambling

new-software-to-predict-addiction-in-an-early-stageA team of researchers and an analytics firm have created an early warning system that notifies gamblers who show signs of addiction at an early stage.

Software analytics start-up BetBuddy has collaborated with researchers from City University London to develop software that determines signs of risk or addiction based on gambling patterns of individuals who voluntarily join a self-exclusion program.

The software’s learning method known as “random forests” could achieve 87% accuracy in predicting playing patterns which were likely to lead in gambling addiction. The system also determines whether or not to send users marketing materials, or whether to suggest self-exclusion to the player.

The research was funded by Innovate UK under its Data Exploration program and is backed by the RCUK Digital Economy Theme, the Engineering and Physical Sciences Research Council (EPSRC), the Economic and Social Research Council (ESRC) and the Defense Science and Technology Laboratory (DSTL).

According to BetBuddy CEO Simo Dragicevic, annual online gambling revenue in Europe alone is expected to reach €13b but it has also created 593,000 problem gamblers based on the National Health Service figures.

“This project is an example of how artificial intelligence and machine learning methods can be used to address an important social problem,” said EPSRC chief executive Philip Nelson.

“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,” added Artur Garcez of City University London.

Losing family more important than losing money

New Australian research shows that problem gambling ads focused on the social consequences of gambling, such as losing family and friends, are more effective than fears of losing money or possessions.

The report is a result of responses from 260 problem and recreational gamblers.

“Problem gamblers are familiar with the lose-win-lose gambling cycle and often lose and win money in the immediate gambling environment, so we see less response to these types of messages,” said Melbourne University researcher Jill Lei.

Lei also added that the study shows that subjects respond to losses that are “difficult or impossible to fix, for instance, when the relationships with friends or family are threatened.”

“Individuals are naturally averse to losses, but loss aversion is often activated only with the prospect of losing something relevant for the individual,” said Lei.


views and opinions expressed are those of the author and do not necessarily reflect those of