New York, Saturday, October 26, 2024- Machine learning AI assisted the US Department of the Treasury in identifying and recovering over $4 billion in fraudulent or improper payments in 2024.
This represents a significant six-fold increase from $652.7 million recovered in 2023, according to the Office of Payment Integrity (OPI).
The OPI, a division of the Bureau of the Fiscal Service, credited AI models for pinpointing high-risk transactions and expediting fraud detection.
The AI technology helped prevent $2.5 billion in fraud, while check fraud detection systems facilitated the recovery of $1 billion. Additionally, enhanced payment processing schedules prevented $180 million in improper payments, and risk-based screening blocked $500 million in potential fraud.
US Deputy Secretary of the Treasury Wally Adeyemo emphasized the importance of AI in safeguarding taxpayer funds. “Helping ensure that agencies pay the right person, in the right amount, at the right time is central to our efforts,” Adeyemo said.
The Treasury’s AI efforts align with broader federal initiatives. The IRS, for example, has been employing machine learning since 2023 to track tax evasion among high-net-worth individuals, while the National Oceanic and Atmospheric Administration (NOAA) uses neural networks for more accurate hurricane predictions.
With online payment fraud predicted to surpass $362 billion by 2028, the Treasury plans to expand its use of AI in collaboration with other federal agencies to combat rising fraud.
