TREAS · TREAS-IRS-9 · record R2859

Vendor Risk Analytics

Department of the Treasury · Internal Revenue Service (IRS)

Overview

Development stage: PilotSource: b) Pilot – The use case has been deployed in a limited test or pilot capacity.
High-impact designation: Presumed high-impact, determined notSource: b) Presumed high-impact, but determined not high impact
Impact justification: AI makes recommendations only and any contracting decisions would go through multiple layers of review by agency officials.
Start date: 2019-04-30 (day precision)Source: 4/30/2019
Withheld from public reporting: NoSource: a) No

Mission

Topic area: Procurement and Financial Management
Operational functions: No function tag matched Derived by keyword rules; see methodology

Problem the AI is intended to solve

Research on vendor risk analytic methods using supervised learning to assess contractor responsibility and whether a prospective vendor would perform successfully. AI can predict potential vendor inability to perform successfully. This capability has the potential to prevent costly, mission-impacting contracting issues. Seminal research and model training in this area was conducted by IRS and Navy personnel who published this paper (https://calhoun.nps.edu/handle/10945/62901). Subsequent, independent federally funded and academic research studies have also found that AI has the potential to improve contractor source selection decision making.

Expected benefits

AI assesses the likelihood of successful contractor performance and identifies vendors at heightened risk of poor performance or non-compliance.

System outputs

Vendor risk assessments output in spreadsheet or dashboard data visualization formats.

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): Not reported
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: No
Demographic features: k) None of the above
Training and evaluation data: Contractor entity and contract transaction data from SAM.gov and USASpending.gov was used to train the models. Contractor entity data is provided by vendors during the contractor registration process. Contract transaction data is reported by federal agency Contracting Officers.
Federal Data Catalog: catalog.data.gov ↗

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