Ending Local and Regional Food Shortages using Community-Engaged Data Science
Title: Ending Local and Regional Food Shortages using Community-Engaged Data Science
Mentor: Walter Bialkowski, PhD, MS
Approach: Thirteen million U.S. households face food insecurity (>10% of all households nationwide)1 representing uncertainty in having, or inability to acquire, enough food to meet the needs of household members due to insufficient money or other resources. The United States addresses food insecurity through many mechanisms, including a hub-spoke model of food warehousing and distribution. Despite robust infrastructure and decades of experience distributing food, unexpected shortages in food at local food pantries still occur. Previous work has utilized data mining and machine learning to build an interactive predictive analytics platform that local food pantries utilize to understand their food shortage risk. Work in the 2023 Summer REU program will extend this work, as well as explore a decentralized application of this technology to predict regional food shortages.
Student Research Activities:
- data management and integration activities to increase the scope of current data sources, and; - utilize statistical modelling, supervised and unsupervised data mining, and machine learning techniques to reveal new insights into the determinants of food shortages, and; - extend work to include statistical modeling of regional food shortages.
Student Background: Students need to have basic computing skills and introductory programming skills in R.