PREDICTORS OF SUCCESS IN MARINE CORPS SPECIAL DUTY ASSIGNMENTS: A MACHINE LEARNING ANALYSIS OF GRADUATION AND TOUR COMPLETION

Loading...
Thumbnail Image
Authors
Gonzalez, Ray M., III
Subjects
United States Marine Corps
Headquarters Marine Corps Special Duty Assignment Screening Team
special duty assignment
retention
Force Design 2030
machine learning
multivariate logistic regressions
recruiting duty
drill instructor
Marine Security Guard Detachment Commander
enlisted assignments
talent management
volunteer
incentive
Least Absolute Shrinkage and Selection Operator
LASSO
elastic net
ridge regression
random forest
Advisors
Seagren, Chad W.
Bacolod, Marigee
Date of Issue
2025-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
The Marine Corps relies on special duty assignments as critical billets for recruiting, training, and safeguarding national assets. High attrition rates at special duty assignment schools and during tours create significant staffing challenges, yet no comprehensive study has analyzed factors contributing to success in these assignments.Using machine learning techniques and multivariate logistic regression models on data from 15,033 Marines across four special duty assignment types (fiscal years 2017–2024), this research develops predictive models to identify characteristics influencing graduation and tour completion success. The analysis evaluates test scores, personal attributes, performance metrics, service history, and demographics.Results indicate that physical fitness scores, personal awards, relative value at processing, volunteer status, and higher grades positively predict graduation success. For tour completion, martial arts qualifications, combat fitness scores, and being married emerge as significant positive predictors. The Basic Recruiter Course demonstrates consistently higher graduation rates compared to other assignments. This research recommends maintaining volunteer incentive programs while developing enhanced screening methods focused on recent performance metrics. The findings provide empirical evidence to improve the Special Duty Assignment Campaign, though model limitations suggest the need for expanded longitudinal data collection.
Type
Thesis
Description
Series/Report No
Manpower Systems Analysis Theses
Department
Department of Defense Management (DDM)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.