Navy Enlistment Supply Model at the Recruiting Station Level

Abstract

Past econometric studies have sought insight into the factors that affect military enlistment supply by creating models based on econometric theory and testing them with data in order to confirm their proposed theoretical relationships. The purpose of this study is to utilize factors common to previous research along with the additional factors of proximity to military installations and high school quality to build the best predictive model. This study utilizes data from 2002 through 2006 to predict high-quality male active-duty Navy enlistments at the recruiting station level. This study shows that neural network models tend to predict the best, followed by regression-based models and then tree-based models. The number of recruiters assigned per Navy Recruiting Station (NRS) and the male 17- to 19-year-old populations proved to be the most important predictive factors. The number of houses, veteran population percentage, land area, percentage of high school students receiving subsidized lunches, Navy installation proximity and per capita were common to all predictive models. This study also finds that NRSs closer to larger navy installations, having higher student-to-teacher ratios, having lower graduation rates (measured by "Promoting Power") and having lower percentages of students on subsidized lunches exhibit greater high-quality male enlistment rates.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2008
Accession Number
ADA483476

Entities

People

  • Claude M. Mcroberts

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Active Duty
  • Algorithms
  • Civilian Personnel
  • Data Mining
  • Data Science
  • Data Sets
  • Economic Analysis
  • Information Processing
  • Information Science
  • Literature Surveys
  • Neural Networks
  • Predictive Modeling
  • Recruiting
  • Statistics
  • Students
  • Training
  • United States

Readers

  • Computational Modeling and Simulation
  • Educational Psychology
  • Naval Personnel Management

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks