Evaluating the Performance of Conformal Prediction Generated Uncertainty Sets in Robust Optimization

Author

Zion C. Johnson

Date of Award

3-2025

Document Type

Thesis

Degree Name

Master of Science in Operations Research

Department

Department of Operational Sciences

First Advisor

Bruce A. Cox, PhD

Abstract

Uncertainty is a major challenge in optimization, especially in problems where unpredictable costs impact decision-making. Robust optimization addresses this by modeling uncertainty via uncertainty sets. These sets are then used such that solutions hold under worst-case scenarios, with success depending on the accuracy of the uncertainty sets. This research examines the use of conformal prediction to construct uncertainty sets for RO, an approach that has not been widely explored. We test split and full conformal prediction in a robust optimization minimum cost flow problem, and comparing them to interval-based and normal-based ellipsoidal uncertainty sets. Experiments run across different network structures and error distributions, including normal, skewed, and bimodal cases. Results show that conformal prediction uncertainty sets perform comparable to traditional methods, with slight variations in performance in terms of solution quality.

AFIT Designator

AFIT-ENS-MS-25-M-186

Comments

An embargo was observed for this posting.

Distribution A: Approved for public release, Distribution Unlimited. PA case number 88ABW-2025-0293

Recommended Citation

Johnson, Zion C., "Evaluating the Performance of Conformal Prediction Generated Uncertainty Sets in Robust Optimization" (2025). Theses and Dissertations. 8280.
https://scholar.afit.edu/etd/8280