FrancePublic sector2014 – ongoingMinistry of Economy and Finance
CFVR tax-audit targeting
France's CFVR system helped target nearly half of business tax audits in 2024
Problem
Tax investigators needed to identify potential fraud across large volumes of records. Suspected anomalies required examination before an audit could begin.
Approach
DGFiP developed CFVR from 2014 to model patterns of possible tax fraud and detect anomalies in its databases. Agents examined the selected files and decided whether an audit was warranted. The ministry reported that these detections supported nearly half of business tax audits in 2024.
Results
Takeaway
CFVR supported case selection while agents retained the decision to investigate. The reported shares measured audit targeting, rather than the accuracy of fraud detection.
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 detection of potential tax anomalies and agents' subsequent review. It reported that detections supported nearly half of business audits and nearly 45% of individual audits in 2024.
Full details are in the original sources.