Predicting Food Insecurity Across U.S. Census Tracts: A Machine Learning Analysis Using the USDA Food Access Research Atlas
DOI:
https://doi.org/10.54536/ajdsai.v2i1.6285Keywords:
Food Insecurity, Machine Learning Models, Predictive Modeling, Random Forest, SHAP Interpretability, Socioeconomic Determinants, USDA Food Access Research Atlas, XgboostAbstract
Food insecurity still poses a serious public-health and social-equity problem in the United States. The USDA Food Access Research Atlas (N = 72,531 census tracts) served as the basis for this study, which not only created but also evaluated machine-learning models to predict the level of food insecurity in a certain tract, which is determined by the lack of supermarkets being accessible to low-income people. The Logistic Regression, Random Forest, and XGBoost classifiers went through training and standard metric comparison. The tree ensemble models (Random Forest and XGBoost) reached remarkable performance (accuracy ≈ 97%, ROC-AUC ≈ 0.99) far above the logistic regression baseline (ROC-AUC ≈ 0.89). SHAP-based model interpretability recognized the poverty rate, median family income, SNAP participation, and vehicle access as the most critical determinants of food insecurity. These results affirm the value of interpretable machine learning in revealing important socioeconomic factors that contribute to food access inequalities, thereby providing a basis for data-informed interventions. The entire analytic process made use of publicly accessible national data, so the results can be reproduced, and future research and policy applications made more transparent.
References
Almalki, A., Brown, G., & Wong, C. (2021). Geospatial and machine learning regression techniques for food access analysis. ISPRS International Journal of Geo-Information, 10(11), 745. https://doi.org/10.3390/ijgi10110745
Amin, M. D., McCluskey, J., & Syed, S. (2020). Predicting access to healthful food retailers with machine learning at the U.S. census tract scale. Applied Geography, 114, 102053. https://pmc.ncbi.nlm.nih.gov/articles/PMC7564312/
Beaulac, J., Kristjansson, E., & Cummins, S. (2009). A systematic review of food deserts, 1966–2007. Preventing Chronic Disease, 6(3), A105. https://stacks.cdc.gov/view/cdc/20366/
Bitto, E. A., Oakland, M. J., & Sand, M. (2003). Solving the problems of Iowa food deserts: Food insecurity and civic structure. Rural Sociology, 68(3), 371–384. https://doi.org/10.1526/0036011053294628
Bronfenbrenner, U. (1979). The ecology of human development: Experiments by nature and design. Harvard University Press.
Chilukuri, J. (2023). Predicting low food access: An empirical assessment of tree-based machine learning models [Preprint]. TechRxiv. https://doi.org/10.36227/techrxiv.16820688.v1
Coleman-Jensen, A., Rabbitt, M. P., Gregory, C. A., & Singh, A. (2021). Household food security in the United States in 2020 (Report No. ERR-298). U.S. Department of Agriculture, Economic Research Service. https://www.ers.usda.gov/webdocs/publications/102076/err-298.pdf
Esmalian, N. A., Coleman, N., Yuan, F., Xiao, X., & Mostafavi, A. (2022). Characterizing equitable access to grocery stores during disasters using location-based data [Preprint]. arXiv. https://arxiv.org/abs/2201.00745
Food and Agriculture Organization of the United Nations. (2026). FAO – Food and Agriculture Organization of the United Nations. https://www.fao.org
Gundersen, C., & Ziliak, J. P. (2021). Food insecurity and health outcomes. Health Affairs, 34(11), 1830–1839. https://pubmed.ncbi.nlm.nih.gov/26526240/
Hu, Y., Yu, Z., & Chen, X. (2022). Integrating predictive analytics with social vulnerability assessment for food insecurity research. Computers, Environment and Urban Systems, 94, 101787. https://doi.org/10.1016/j.compenvurbsys.2022.101787
Jiao, J., Moudon, A. V., Ulmer, J., Hurvitz, P. M., & Drewnowski, A. (2012). How to identify food deserts: Measuring physical and economic access to supermarkets in King County, Washington. American Journal of Public Health, 102(10), e32–e39. https://doi.org/10.2105/AJPH.2012.300675
Kapoor, S., & Sayer, S. (2024). From bytes to bites: Using country-specific machine learning models to predict famine and food insecurity [Preprint]. arXiv. https://arxiv.org/pdf/2409.09980
Kwan, M. P. (2021). Geospatial analysis and data science in public health research. Annals of GIS, 27(4), 341–354. https://doi.org/10.1080/19475683.2021.1970269
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (Vol. 30). https://arxiv.org/abs/1705.07874
Marmot, M., & Wilkinson, R. (2005). Social determinants of health (2nd ed.). Oxford University Press.
Salari, M., Kramer, M. R., Reyna, M. A., Taylor, H. A., & Clifford, G. D. (2023). Combining crowd-sourcing, census data, and public review forums for real-time, high-resolution food desert estimation. BioMedical Engineering OnLine, 22, 69. https://doi.org/10.1186/s12938-023-01108-9
Smith, M. D. (2020). Food insecurity, gender, and international migration in low-income countries. Food Policy, 91, 101838. https://doi.org/10.1016/j.foodpol.2020.101838
Tango, P. (2023). On the forecastability of food insecurity. Scientific Reports, 13, 4309. https://pmc.ncbi.nlm.nih.gov/articles/PMC10038988/
Walker, R. E., Keane, C. R., & Burke, J. G. (2010). Disparities and access to healthy food in the United States: A review of food deserts literature. Health & Place, 16(5), 876–884. https://doi.org/10.1016/j.healthplace.2010.04.013
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Oluwatosin Lawal, Awele Okolie, Callistus Obunadike, Prince Michael Akwabeng, Mark Onons Ikhifa, Paschal Alumona
This work is licensed under a Creative Commons Attribution 4.0 International License.
