Predicting Pilot Success Using Machine Learning

Abstract

The United States Air Force has a pilot shortage. Unfortunately, training an Air Force pilot requires significant time and resources. Thus, diligence and expediency are critical in selecting those pilot candidates with a strong possibility of success. This research applies multivariate and statistical machine learning techniques to pilot candidates pre-qualification test data and undergraduate pilot training results to determine whether there are selected re-qualification tests or specific training evaluations that do a best job of screening for successful pilot training candidates and distinguished graduates. Flight experience, both during training and otherwise, indicates pilot training completion and performance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2020
Accession Number
AD1101488

Entities

People

  • Aaron C Giddings

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Air Force Personnel
  • Air Force Research Laboratories
  • Aircrafts
  • Airplanes
  • Algorithms
  • Artificial Intelligence
  • Computational Science
  • Data Sets
  • Department Of Defense
  • Education
  • Enlisted Personnel
  • Flight Training
  • Governments
  • Machine Learning
  • Military Pilots
  • Neural Networks
  • Personnel Management
  • Probabilistic Models
  • Psychological Tests
  • Psychology
  • Students
  • Training
  • United States
  • United States Government
  • Unmanned Aerial Vehicles

Readers

  • Aviation Science / Aeronautics.
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks