DOL · DOL-20 · record R1290

Scanner Data Product Classification

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: 2019-03-01 (day precision)Source: 03/01/2019 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 receives bulk data from some corporations related to the cost of goods they sell and services they provide. Consumer Price Index (CPI) staff have hand-coded a segment of the items in these data into Entry Level Item (ELI) codes. To accept and make use of these bulk data transfers at scale, BLS has begun to use machine learning to label data with ELI codes. The machine learning model takes as input word frequency counts from item descriptions. Logistic regression is then used to estimate the probability of each item being classified in each ELI category based on the word frequency categorizations. The highest probability category is selected for inclusion in the data. Any selected classifications that do not meet a certain probability threshold are flagged for human review. Benefits: real-time turnaround, productivity improvements, cost savings.

Expected benefits

Efficiency of item classification efforts

System outputs

Entry Level Item Codes

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: Agency Generated; respondent-provided category and product description information
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