NYT: DraftKings Built an 'Elasticity' Model That Scored Bettors by How Much They Would Lose

Tech Times (reporting on The New York Times)·high signalXBlueskyLinkedInCopy link

A New York Times investigation found DraftKings built a machine learning model in 2023 that scored customers by expected losses after receiving a free bet, called the score 'elasticity,' and used it to direct hundreds of millions of dollars in promotional spend; executives credit AI-driven promotions with a 13% sportsbook margin improvement in 2025. The model read play frequency, account balances and loss-to-wager ratios, and former employees said its logic surfaced problem gamblers as the most lucrative targets while a parallel effort to build gambling-harm risk scores from the same data was shelved. DraftKings says it 'rejects any implication' that its marketing unfairly targets customers.