Close this search box.
Messina Group helped our client gain crucial insights into store performance, efficiently allocate their labor, and better manage costs within their restaurants by using advanced analytics and machine learning.

Artificial Intelligence

Restaurant Management Group Leverages Advanced Analytics and Machine Learning to Optimize Labor Across 700 Stores

Print Friendly and PDF

Client Profile & Challenge

Our client is a $700 Million+ Restaurant Management Group operating over 700 locations across nine concepts.


This client needed a data-driven solution to efficiently allocate their labor and better manage costs within their restaurants. The solution needed to be flexible to account for variances across concepts, geographies, menu mix, and ordering profiles (online/in-store) and provide the optimal labor model per time of day and day of the week for each store.

Solution Overview

Utilizing our cloud data warehouse with granular sales and labor data for each store, geography, and concept, Messina Group developed Machine Learning models & AI to analyze each cross-section of data and recommend the optimal labor model in each store. Utilizing the key metrics Traffic per Labor Hour (TPLH) and Sales per Labor Hour (SPLH), our client could visualize the model’s impact for store, district, and regional managers across all concepts.


Advanced Analytics, Artificial Intelligence (AI), ML, Data Visualization

Technology Used:

Microsoft Azure, Microsoft Power BI, Python


Upon implementation, our client swiftly gained crucial insights into store performance, measured by TPLH/SPLH across various parameters such as district, region, day of the week, time of day, and more. This initiative laid the foundation for benchmarking the performance of each store, district, and concept.

Forward-looking ML models facilitated the generation of well-informed staffing recommendations tailored to individual stores. These recommendations were based on the project volume and sale patterns for each day of the week and time per day.

By diligently comparing outcomes against the established baseline and assessing the resultant impact, each conceptual division substantially refined their labor model, significantly optimizing our client’s labor model and, by extension, their labor spend.