Determination of Low-Cost Grocery Store Locations Using GIS and Machine Learning: Omaha, Nebraska Case Study

Authors

  • Oluwafisayo Adeniyan

Abstract

Access to affordable and nutritious food is a pressing issue in Omaha, Nebraska, where economically disadvantaged neighborhoods face significant barriers due to the lack of nearby grocery stores. This study addresses the problem of food deserts, defined by low median household income and high obesity rates, using a data-driven approach that integrates Geographic Information Systems (GIS) and machine learning to identify underserved areas and optimize grocery store placement.
GIS analysis revealed that neighborhoods such as Cathedral, Downtown, Benson, Keystone, and North Omaha are food deserts with limited access to transit and grocery stores, exacerbating food insecurity. Spatial mapping highlighted a disparity in food store distribution, with central Omaha benefiting from better access compared to northern and western regions. Using predictive modeling, Random Forest and Regularized Decision Tree algorithms achieved perfect classification of food desert neighborhoods. These models also identified Cathedral and Downtown as areas with the highest grocery demand, calculated by combining food desert probability with population density.
The study evaluated the potential impact of adding grocery stores to high-demand areas through simulations, which demonstrated significant reductions in travel distances to food sources and enhanced access for underserved communities. A cost-benefit analysis indicated the economic feasibility of the intervention, estimating a net benefit of $15 million from the construction of five new grocery stores, considering reductions in healthcare costs, obesity rates, and economic benefits to the neighborhoods.
This research offers actionable insights for policymakers and urban planners, emphasizing the need for targeted grocery store placement, policy incentives, and community engagement. The integration of GIS and machine learning provides a scalable framework for addressing food insecurity, which can be adapted to other urban areas facing similar challenges. By improving food access in Omaha, this study highlights the potential to enhance health equity, foster community resilience, and drive meaningful social and economic change.

Downloads

Published

2025-07-16

How to Cite

Adeniyan, O. (2025). Determination of Low-Cost Grocery Store Locations Using GIS and Machine Learning: Omaha, Nebraska Case Study. Digital Repository of Theses - SSBM Geneva. Retrieved from https://repository.e-ssbm.com/index.php/rps/article/view/914