FrancePublic sector2014 – ongoingFrench public finance directorate (DGFiP)
CFVR identification of potential tax fraud for human review
DGFiP's CFVR detections supported nearly 45% of individual tax audits in 2024
Problem
Tax officials needed to identify anomalies and potential fraud in tax data before selecting cases for investigation.
Approach
DGFiP developed CFVR from 2014 to detect potential anomalies automatically. Officials examined flagged files and decided whether an audit was justified. The ministry identified CFVR as a deployed AI programme.
Results
Takeaway
CFVR supported case selection while officials retained the decision to investigate. Audit coverage did not establish the system's accuracy or additional tax recovered.
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
- Evidence
- Company's own claim
Sources
Source summaries
The ministry described CFVR's automatic detection of potential tax anomalies and subsequent review by officials. It attributed nearly half of business audits and nearly 45% of individual audits in 2024 to these detections.
Full details are in the original sources.