Predicting Skilled Workforce Retention: A Machine Learning Approach with Royal Australian Navy Sailors

Tom Ahn, Stephen Cole, James Fan, Christopher Griffin

Research output: Contribution to journalArticlepeer-review


Skilled workers can be difficult and expensive to recruit, train, and retain. This is particularly true for military organizations, such as the Royal Australian Navy (RAN). Retention of both technical and nontechnical sailors is critical to future manning continuity and capability of the RAN. This research employs machine learning to analyze RAN exit survey data collected between 1999 and 2018 to predict the attitudes and behaviors of technical and nontechnical sailors voluntarily leaving the service. We find that machine learning can accurately detect differences in the attitudes and behaviors of senior technical and nontechnical sailors, as well as identify differences in sentiment across periods covering key career milestones. Our results inform current and future retention policies, both military and civilian.

Original languageEnglish (US)
Pages (from-to)23-53
Number of pages31
JournalMilitary Operations Research (United States)
Issue number2
StatePublished - 2023

All Science Journal Classification (ASJC) codes

  • Safety Research
  • Sociology and Political Science
  • Political Science and International Relations

Cite this