Understanding the Impact of Socio-economic Factors on Navy Accessions

Navy Recruiting Command (NRC) must efficiently allocate its primary recruiting resource, recruiters, to areas with the greatest potential for generating recruits to improve Navy enlisted accessions in a fiscally constrained environment. Our research builds on work in this area and makes use of open source socioeconomic data sets, including from the Internal Revenue Service (IRS) and the Federal Bureau of Investigation (FBI). Beginning with a response variable of annual Navy accessions and a set of 71 explanatory variables populated from zip code-level data, we fit and validate multiple linear regression models for data at the station level and a zero-inflated negative binomial (ZINB) regression model for data at the zip code level. We identify the average number of recruiters, adjusted gross income, and total veterans as the principal drivers of accession production at the station level. We test each model with out-of-sample data. We observe improved prediction rates compared to previous zero-inflated Poisson models using similar recruiting data.