DOL · DOL-36 · record R1302

Sample Refinement: Frame API

Department of Labor · BLS

Overview

Development stage: DeployedSource: c) Deployed – The use case is being actively authorized or utilized to support the functions or mission of an agency.
High-impact designation: Not high-impactSource: c) Not high-impact
Impact justification: Used for survey processing for statistical purposes
Start date: 2024-09-20 (day precision)Source: 09/20/2024 00:00:00
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Other: Applied Mathematical SciencesSource: Other - Applied Mathematical Sciences
Operational functions: No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

BLS establishment-based surveys, such as the Survey of Occupational Injuries and Illnesses (SOII), the National Compensation Survey (NCS), and the Occupational Requirements Survey (ORS), use the Longitudinal Database (LDB) as the frame for their survey samples. For each of these programs, there is a significant time-lag between when the sample is drawn for a program and when data collection begins. A critical and time-consuming part of data collection is sample refinement: checking the latest Quarterly Census of Employment and Wages (QCEW) and LDB data to adjust for any changes to the sampled establishment during that time-lag. The QCEW/LDB Frame API allows fast retrieval of the latest QCEW/LDB data for a nationwide sample so that users can perform sample refinement more efficiently. The SOII program uses the Frame API to perform over 20 sample refinement comparison checks, which outputs a report for the data collectors. The Frame API uses TF-IDF vectors and cosine similarity to compare company names, mailing addresses, and unit descriptions between the survey sample and the latest QCEW/LDB data to determine what components may have changed. The Frame API also has the flexibility for the users to match records using other combinations of variables.

Expected benefits

Efficiency and data quality improvements

System outputs

Similarity score between records

Technology

AI classification: Classical / predictive MLSource: Classical/Predictive Machine Learning: Models trained on data to make predictions or classifications based on identified patterns or relatio…
System name(s): BLS Internal System
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Developed in-houseSource: b) Developed in-house
Vendor (as reported): Not reported
Vendors (standardized): None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII: No
Privacy Impact Assessment: Not reported
Authorization to Operate: Yes
Demographic features: k) None of the above
Training and evaluation data: SOII and QCEW records
Federal Data Catalog: Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Pre-deployment testingNo answer reported

AI impact assessmentNo answer reported

Independent reviewNo answer reported

Ongoing monitoringNo answer reported

Operator trainingNo answer reported

Fail-safeNo answer reported

Appeal processNo answer reported

User and public consultationNo answer reported

Potential impacts and how they were identified

Not reported