Government SI Register · SSA · High impact

Pre-Effectuation Review (PER) / Targeted Denial Review (TDR) Models

The Social Security Administration lists "Pre-Effectuation Review (PER) / Targeted Denial Review (TDR) Models" in the 2025 federal inventory as a high impact SI use case at the deployed stage, in Chief Information Officer, Analytics and Improvements. In the agency's words, the problem it is meant to solve: "This AI use case identifies high likelihood of error in certain claims and refers them for review. This use case reduces incorrect benefits payment." Every field below is quoted as filed.

ID none givenStage DeployedSource row 2813

The record, as filed

Every field the agency reported

Bureau or component
Chief Information Officer, Analytics and Improvements
Stage
Deployed
High impact status
High-impact
Topic area
Benefits Processing
Technology type
Classical ML
Problem it is meant to solve
This AI use case identifies high likelihood of error in certain claims and refers them for review. This use case reduces incorrect benefits payment.
Expected benefits
Pre-Effectuation Review (PER) and Targeted Denial Review (TDR) benefit public, taxpayers, and claimants in ensuring that SSA provides benefits for those who qualify for benefits based on the SSA policy and guidelines.
What the system outputs
Probability scores via an in-line mainframe process
Operational or pilot start
12/1/2003 0:00
How it was built or bought
In-house Development
Authorization to Operate
No
System name
PER TDR
Data used to train, tune or evaluate
Models use administrative data for Title II (retirement, survivors, and disability benefits) and Title XVI (Supplemental Security Income) programs including form SSA-831 (Disability Determination and Transmittal) data.
Federal Data Catalog link
It is not publicly disclosed.
Uses personally identifiable information
Yes
Demographic features used
c) Age
Custom-developed code
No
Public source code
No
Pre-deployment testing
Yes
Impact assessment completed
Yes
Potential impacts identified
False positives for the models may impact a claimant's accurate processing of their application. Ideally we would like only those qualifying for benefits should get on and remain on the rolls.
Independent review
CAIO Review
Ongoing monitoring
Yes - Monitoring Established
Operator training
Training Established
Fail-safe
Not Applicable
Appeal process
Appeal Process Established
Consultation with users and the public
Other

Left blank in the record: Justification given, Vendors, Privacy Impact Assessment. Point of contact details are in the source file.

Source

Source: row 2813 of 2025_individually_reported_AI_use_cases.csv in OMB's 2025 Federal Agency AI Use Case Inventory repository (summary as of April 13, 2026), read Nov 17, 2026. File SHA-256 a62721202ca4b110

Life areas: Benefits.

Records, not ratings. Every entry is what an agency reported to OMB, quoted as filed. The register does not test, rate or vouch for any system, and a record does not prove how a system is used day to day.