Subledger Data Quality Machine Learning

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

2021-04-21 (day precision)Source: 2021-04-21T00:00:00

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

Ginnie Mae analyzes Master Sub-Servicer (MSS) transaction data on a monthly cadence. The AI solution allows Ginnie Mae to detect anomalies in this data that would not be detected via traditional methods.

Expected benefits

Through its use of machine learning models, Ginnie Mae has enhanced its ability to identify data inconsistencies and exceptions associated with its MSS transaction data. Through the early detection of these anomalies, Ginnie Mae is able to reduce manual adjustments to financial reporting, which yields cost and time savings.

System outputs

Data anomalies

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)

Ginnie Mae Financial Accounting System

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)

Ernst & Young

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

This is not a self-learning or self-refining system. Although the data is not used to train, fine-tune, and/or evaluate performance, the following sources are used: - Transaction data from Ginnie Mae Master Sub-Servicers for the defaulted Single-Family non-pooled assets (this data does not include any PII).

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.

Potential impacts and how they were identified

Not reported