Utilizing Patterns in US Military Interventions to Improve Logistics Decision Making

Abstract

The field of political science has had difficulty predicting where the next conflict will occur using strictly quantitative methods. However once a conflict does occur, there seems to be some logical variables such as oil or level of democracy that contribute to the US's willingness to commit military forces abroad. How these variables relate and interact in determining the US decision of whether or not to enter a conflict is a difficult matter. No known traditional linear model to predict US conflict decisions has been formulated. This research proposes a list of variables that might impact intervention decisions and puts forth a neural network approach to analyzing the underlying interactions present in existing conflict data. This method explores the interactive and possibly non-linear nature of conflict decision making. The results indicate that a reasonably small number of variables can be used to predict when the US might enter a conflict. Finally, the results of this analysis are then applied to a logistics location problem in order to show how eliminating some degree of uncertainty might significantly improve inventory positioning decisions.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 17, 2002
Accession Number
ADA398515

Entities

People

  • John E. Bell

Organizations

  • Auburn University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Cold War
  • Computer Programming
  • Data Sets
  • Databases
  • Emergency Response
  • International Conflicts
  • International Organizations
  • Intervention
  • Logistics
  • Military Equipment
  • National Politics
  • National Security
  • Neural Networks
  • Political Science
  • War

Readers

  • Political Violence and Terrorism Studies.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks