DraftKings used a machine-learning model to target gamblers most likely to lose, while a risk-detection effort was reportedly shelved.

The model examined play frequency, account balances, loss-to-wager ratios, and a separate estimate of whether a user was likely to stop gambling altogether, according to the Times. A higher score meant a customer was predicted to generate more revenue per promotional dollar spent.

Jayden Butts, a former DraftKings data analyst, described the underlying logic to the Times: “We are looking for traits and features that we can target that indicate a good investment.”

The best investment would be a problem gambler. (According to Jayden Butts, former DraftKings data analyst, to The New York Times)

DraftKings executives said data science and analytics improved promotion-driven sportsbook margins by 13% in 2025, and that AI helped personalize hundreds of millions of dollars in promotional spending, according to the Times.