Date of Award

3-2023

Document Type

Thesis

Degree Name

Master of Science in Operations Research

Department

Department of Operational Sciences

First Advisor

Michael J. Garee, PhD

Abstract

The United States Air Force (USAF) has struggled with a sustained pilot shortage over the past several years; senior military and government leaders have been working towards a solution to the problem, with no noticeable improvements. Both attrition of more experienced pilots as well as wash out rates within pilot training contribute to this issue. This research focuses on pilot training attrition. Improving the process for selecting pilot candidates can reduce the number of candidates who fail. This research uses historical specialized undergraduate pilot training (SUPT) data and leverages select machine learning techniques to determine which factors are associated with success in SUPT. Humanly understandable (known as interpretable) machine learning techniques will be used to predict SUPT outcome, as these models provide justifications for these predictions and build trust with decision-makers. Three interpretable models were considered, including two rule-based models and one tree-based model. PCSM score was identified as the strongest predictor for success. The best performing model achieved an F1 score of 0.93, compared to 0.84 and 0.77 for the other models. The results of this research emphasizes the usefulness of interpretable models and their ability to inform a decision-maker, assisting them in their selection of future pilots.

AFIT Designator

AFIT-ENS-MS-23-M-134

Comments

A 12-month embargo was observed.

Approved for public release. Case number on file.

Share

COinS