Irineo Cabreros

Tasked with developing a new capability for U.S. Air Force human resources planners, the authors have developed an initial prediction prototype tool that can be used to alert decisionmakers of emerging problems and thus allow them enough time to consider adjusting accession and retention policies before shortages occur.

Using an updated version of RAND's Recruiting Resource Model, the authors analyze the relationship between observed and alternative mixes of Army spending on recruiting resources (advertising, recruiters, and bonuses) and recruiting outcomes, particularly contracts and accessions. Results indicate that TV advertising and, to a lesser extent, recruiters are more cost-effective than bonuses at increasing enlistments.

The U.S. Department of Defense (DoD) is investing heavily in the development of machine learning (ML) algorithms to assist in many decisionmaking processes. This report provides policymakers and developers of ML algorithms with a framework and tools to produce algorithms for personnel management that are consistent with DoD's equity priorities.

Several U.S. Army resources and policies work together to produce recruits. Understanding their interactions under various circumstances enables the Army to use its limited resources more effectively and efficiently. The authors present a model--the Reserve Recruiting Resource Model--designed to optimize resources and policies to achieve future Army Reserve recruiting goals.