United StatesPublic sector2015 – ongoingSocial Security Administration
Insight quality checks for disability adjudication
Social Security deployed Insight to flag potential quality issues in disability decisions
Approach
SSA attorney Kurt Glaze proposed Insight in 2015. The software extracted information from decision text, combined it with structured case data and applied rules and probabilistic machine learning to flag potential issues. It was fully deployed at the appeals level in late 2017 and hearings level in late 2018. Staff retained responsibility for decisions and remedies.
Results
No published figures
Takeaway
Insight supplied quality feedback during existing review work. Formal evaluation of its effects on accuracy and remand rates remained limited.
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 authors, including Insight's creator, documented its development and deployment. They described SSA internal findings of better quality and processing efficiency, while acknowledging limited formal impact evaluation.
Full details are in the original sources.
Problem
Disability decision writers and reviewers worked through separate handoffs. Potential inconsistencies or missing findings could persist until later review.