United StatesPublic sector2024 – ongoingU.S. Department of the Treasury
Machine-learning identification of Treasury check fraud
Treasury attributed $1 billion in recoveries to faster check-fraud detection using machine learning
Problem
Treasury faced increased fraud and improper payments following the pandemic. Its payment-integrity operation needed to identify fraudulent checks faster.
Approach
The Bureau of the Fiscal Service's Office of Payment Integrity used machine learning to accelerate identification of Treasury check fraud. This operated alongside other fraud-prevention and payment-processing measures. Treasury separately attributed recoveries to the machine-learning check-fraud work.
Results
Takeaway
The check-fraud recovery figure was one component of Treasury's wider payment-integrity results. The broader total included measures beyond machine learning.
Categories
- Size
- Large enterprise
- Industry
- Public sector
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
Treasury attributed $1 billion in recoveries to machine-learning check-fraud identification. Its wider total combined several prevention and recovery measures.
Full details are in the original sources.