How DraftKings Uses A.I. to Target the Gamblers Likeliest to Lose

SS: inb4 "AI? you mean OLS with constructed regressors"

The Times interviewed more than 40 former DraftKings employees, and obtained internal research memos, presentations and Slack messages as well as betting records from experiments conducted on customers.

The documents show how the model [former employee] Jayden Butts worked on analyzed dozens of data points for each gambler, including how frequently they played, their daily account balances and how much they typically lost compared with how much they bet. It also incorporated another model that calculated how likely a user was to stop gambling.

This betting data may also contain signs that a person is headed for trouble. Yet when employees developed a machine learning model that would have assigned users “risk scores,” the company sidelined it, according to two former employees who worked on that project.

“It is as predatory as it sounds,” said a former DraftKings analyst who, like many interviewed for this article, requested anonymity because he feared retribution. “If you lose more, we give you more, so you keep playing more.” He quit in 2024.

(…)

DraftKings already had a system that weighed factors like a gambler’s skill, how much they bet and tax rates on gambling revenue in the state where they lived.

But it was relatively crude. According to one internal memo, it offered “no information or insight on expected user-level profitability of reinvestment dollars” — in other words, DraftKings did not know how effective its promotions were at inducing gamblers to lose.

Figuring this out required machine learning. Unlike traditional data analytics, where researchers decide which patterns to look for, machine learning models can sift through hundreds of variables on their own to find combinations that help predict particular behaviors.

Data scientists had trained the new casino model on historical data. It was Mr. Butts’s job to test it on real customers. Each week, the model vacuumed up information about a user’s recent activity. The score it calculated was known internally as “elasticity,” a term borrowed from economics.

Users with below-average scores were deemed “inelastic” and marked for fewer incentives. The “elastic” bettors remained.

In September 2023, Mr. Butts tested using the elasticity model to influence promotions for about 5,000 casino players. He later expanded the tests to a larger population.

He initially thought DraftKings aimed to save money by avoiding people who were unlikely to be profitable. But he said his supervisors told him that the company did not want to reduce its promotional spending but rather to “redeploy” it. He understood this to mean the goal was to direct more promotions toward the biggest losers.

Mr. Butts said he also worried that his experiments might lead DraftKings to send more promotions to players who played more addictive games, including his own former vice: online slots, widely regarded by public health experts as among the most addictive forms of gambling.

It’s not clear the extent to which DraftKings has targeted slots players more than others. But in a 2023 internal memo, researchers reported that slots revenue was “more elastic” than earnings from other casino games, meaning that promotions were particularly effective at driving users to those games. A Times analysis of internal DraftKings casino betting data from early 2024 also found that bettors with high elasticity scores gambled more on slots, on average, than those with low scores.

this is pretty well known among people who either use or or have worked on these apps. sports betting is as much of a child of the data science revolution as much as regulatory easing – automatic bookies just can't work without a massive amount of user-level market segmentation since small mispricings will be adversarially selected against by smart betters. so the business model relies on systematically cutting off successful betters while catering heavily towards unsuccessful betters.

nate silver argued ages ago that a good regulatory move might just be to restrictthis kind of market segmentation which would force these businesses to actually take risk. although admittedly it seems like kind of an evil vice industry anyways t b h