# Optimizing Food Establishment Inspections through Modeling

> **NIH FDA U18** · MUNICIPALITY OF ANCHORAGE · 2020 · $69,097

## Abstract

Project Summary/Abstract
This project will help reduce foodborne illness in the Municipality of Anchorage (MOA)
by optimizing the methodology of when regulated food facilities are inspected. This
project will utilize and adapt an open source predictive data analytics platform
developed by the City of Chicago to predict which regulated food facilities are most
likely to have critical violations. By using this innovative technology, the MOA can
change its inspection approach to conduct inspections of facilities that are predicted by
the model to be higher risk and have critical violations. This will help the MOA target
facilities that have a higher risk of foodborne illness and help protect the community as
a whole. Data collected from many sources will be used to optimize the order in which
inspections are done. These sources include previous inspection history, how long it
has been since the last inspection, whether or not the establishment has a liquor license
and a host of other data points that help rank the risk of violations occurring in each
facility. The data model will then rank all the facilities based on how many factors the
data model finds. Then the model will rank the facilities so that they can prioritized for
inspection sooner than they would be using the traditional method of inspection order.
This will allow the MOA to find facilities with problems sooner than normal. In the
Chicago study they found that facilities were inspected seven days sooner than using
traditional methods for inspection order.
This proposal will also allow the MOA to develop new educational materials and short
videos that will be used to help educate facilities found with critical violations with
methods on how to prevent these violations and thus lower the risk of foodborne illness.
Once this data model is operating the program will be able to track over time whether
the intervention methods put into place are effective by looking at whether facilities
remain high risk or improve. By tracking progress of facilities over time the program will
be able to adjust interventions to improve compliance and reduce the risk of foodborne
illness across the MOA.

## Key facts

- **NIH application ID:** 10134078
- **Project number:** 1U18FD007011-01
- **Recipient organization:** MUNICIPALITY OF ANCHORAGE
- **Principal Investigator:** Brendan Babb
- **Activity code:** U18 (R01, R21, SBIR, etc.)
- **Funding institute:** FDA
- **Fiscal year:** 2020
- **Award amount:** $69,097
- **Award type:** 1
- **Project period:** 2020-07-01 → 2022-06-30

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10134078

## Citation

> US National Institutes of Health, RePORTER application 10134078, Optimizing Food Establishment Inspections through Modeling (1U18FD007011-01). Retrieved via AI Analytics 2026-05-26 from https://api.ai-analytics.org/grant/nih/10134078. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*