Data mining can help identify problem gamblers

ABC News studied the problem of identifying potentially compulsive gamblers Wednesday in an article which carried within it a reminder of the significant value delivered by a major Bwin – Harvard Medical School collaboration during a 2005 study of the subject.

The article recalled the project, in which Bwin delivered massive amounts of relevant gambling data gleaned from the detailed records which most online gambling companies routinely amass on player behaviour.

Harvard’s Cambridge Health Alliance then used the data to formulate indicators for problem gambling, a process that continues to deliver valuable insights to this day.

Cambridge Health Alliance’s associate director of research, Dr. Sarah Nelson, who is also an assistant professor of psychiatry at Harvard Medical, told ABC News that the Bwin data was used to start creating an epidemiology of gambling: how much a gambler spends, how much time is spent gambling.

“We then went on to try to figure out if we could use that to predict which people might run into trouble and to intervene before they develop problems,” she said, revealing that the information remains valuable today.

In May this year Nelson presented her most recent findings at a conference in Las Vegas, noting that certain variables seem to be particularly important for predicting which gamblers may become addicts.

These include unevenness in the amounts of bets, she says, “People who are all over the map turn up as people with problems.”

The number of different games played also correlates with problem gambling: the greater the variety, the more likely the problem.

However, Nelson cautions that the level of accuracy of the diagnostic tool she and her colleagues have developed – called the “Sports Bettor Algorithm 1.1”- is still quite low. But there is a correlation between certain behaviours and addiction.

Industry reaction to her work and to other research like it has been mixed, ABC News reports, noting that some casino executives do not believe that problem gamblers can be identified by play patterns.

Focal Research Consultants believes they can. CEO Tony Schellinck made the news this week with claims that his company has practical experience in identifying potential problem gamblers from their playing patterns as recorded by loyalty programs .

Schellinck told ABC News that his company has spent 15 years developing its own early-detection algorithm. The system Focal Research sells, called Alert, has a starting price of $500,000 and has been used by seven gaming clients in the past eight years, he said.

“It really does work,” Schellinck claimed. “We’ve done dozens of major peer-review studies, all public” Two government-run Canadian casinos, he says, used Alert for over seven years as part of a program they called “I Care.”

When Alert told managers that a customer was showing addictive behavior, a staff member would be dispatched to tactfully intervene.

Single indicators may not be sufficient to identify a problem, but taken together, several factors can flag a potential problem, Schellinck says.

“We examine the behaviour of people as they gamble, through their loyalty cards. We analyse that information. Certain behaviours, when in combination, allow us to say, yes, this person is at high risk of becoming an addict or is one right now,” he explained.

Schellinck said that experience has shown that the vast majority of problem gamblers are not big spenders. They’re people who are spending around $200 a month on their habit but can’t afford to do so.

Related and similar