DHS · DHS-P1 · record R1978

Normalization Services

Department of Homeland Security · ICE

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: Not reported
Start date: 2021-04-01 (day precision)Source: 2021-04-01T00:00:00
Withheld from public reporting: Not reported

Mission

Topic area: Law Enforcement
Operational functions: Search and knowledge retrieval Derived by keyword rules; see methodology

Problem the AI is intended to solve

This use case intends to solve the problem of data redundancies, inconsistencies difficult to integrate data that hinders the efficiency and accuracy of investigations.

Expected benefits

HSI utilizes artificial intelligence to enhance data accuracy and efficiency by verifying, validating, correcting, and normalizing various types of information, including addresses, phone numbers, names, and ID numbers. This process helps to eliminate data entry errors, detect intentional misidentification, and connect related information across multiple datasets, ultimately reducing the time and resources required for investigations. The machine learning-powered normalization services offered by HSI include converting ambiguous addresses into usable formats, identifying ID types from partial information, categorizing names with complex suffixes and family names, and standardizing phone numbers to the E164 format, including determining their originating county. By normalizing and improving the quality of investigative datasets, HSI is able to use more advanced tools to find correlations and leads that would have otherwise gone undetected without extensive manual effort.

System outputs

The output includes normalized data that improves search capability during investigations. This includes normalizing data to update less well-defined addresses into usable addresses for analysis- (such as those using mile markers instead of a street number); inferring ID type based on user-provided ID value (such as distinguishing a SSN from a DL number without additional context); categorizing name parts while taking into account additional factors (including generational suffixes and multi-part family names); and validating and normalizing phone numbers to the E164 standard, including their identified county of origin.

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): Repository for Analytics in a Virtualized Environment
Custom-developed code: Yes
Public source code: Not reported

Sourcing

How it was built: Contract and in-houseSource: c) Developed with both contracting and in-house resources
Vendor (as reported): Booz Allen
Vendors (standardized): Booz Allen Hamilton

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

Data and privacy

Involves PII: Yes
Privacy Impact Assessment: www.dhs.gov ↗
Authorization to Operate: Yes
Demographic features: Not reported
Training and evaluation data: Data holdings within HSI case files that require normalization (e.g. subpoenaed phone record). This includes, but is not limited to, evidentiary records containing phone numbers, names, addresses, and ID numbers.
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