The Utility of Machine Learning Applied to Military Assessment and Selection
No Thumbnail Available
Authors
Deverill, Hayden
Scherer, William
Porter, Michael
Stam, Allan
Issue Date
2024-08-01
Type
Journal articles
Language
Keywords
Machine Learning , Military Assessment and Selection , Center for Data Analysis and Statistics
Alternative Title
Abstract
This paper presents a case study of how to use machine learning to provide actionable recommendations in the military assessment and selection (A&S) context. Military units use an in-depth A&S process to acquire the most qualified candidates. The specific A&S we studied had 11,885 candidate records collected over a five-year period with 89 total features that included administrative, performance, and psychological data on each candidate. We applied a robust machine learning approach involving feature engineering, feature selection, optimized predictive models, and data subsets analysis to extract meaningful information from the data. Our objective for this research was to evaluate the utility of applying machine learning techniques to a specific military A&S dataset with the goal of improving the holistic A&S selection process. The research resulted in valuable insights from the data that found features highly predictive of candidate nonselection, learned methods to modify the existing data to improve predictive capability, and informed actionable recommendations for the A&S selection process.
Description
Citation
Deverill, Hayden, William Scherer, Michael Porter, and Allan Stam. “The Utility of Machine Learning Applied to Military Assessment and Selection.” Military Operations Research 29, no. 2 (2024): 53–94. https://www.jstor.org/stable/27317896.
Publisher
Military Operations Research Journal