Joseph Martin, & Dr. Isaac Quintanilla Salinas
In the United States, obtaining diapers for underserved families is an urgent social problem to solve, as most families are “living diaper to diaper.” In this study, we utilize geographic information systems and unsupervised machine learning techniques to determine an optimal location for a diaper distribution center in Ventura County. We applied a k-means clustering algorithm to publicly-available data obtained from the United States Census Bureau on the population of infants and families living at or below 200% of the federal poverty level, as well as the latitude and longitude coordinates of tract centroids to determine optimal grouping. Potential locations were identified with data-weighted centroids of the generated clusters. Viability of these locations was assessed according to proximity to major bus routes and population of families in need within a 30 minute walking distance. Our findings highlight potential areas for increasing diaper access for underserved families in south Oxnard, CA.