Data-driven Dynamic Decision-making - Using Discrete Optimization and Supervised Machine Learning

Aug 3, 2026

This Ph.D. thesis advances data-driven optimization for complex combinatorial problems by integrating machine learning with optimization to accelerate online decision-making. In airline operations recovery, it uses supervised machine learning and decision-aware binary classification to prune the decision space, overcoming slow exact methods and weak heuristics while improving runtime and solution quality. In occult hemorrhage diagnosis, it builds a multisensor, vital-sign framework that updates patient risk over time under capacity constraints and optimizes admissions, reducing false positives and missed diagnoses.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages167

Reading Time7 h 1 min

AccessFree to download

Abstract

Airline operations recovery

Healthcare diagnosis of occult hemorrhage

Experimental results and outcomes

Acknowledgements

Dartmouth College Dartmouth Digital Commons | Dartmouth College Ph. D Dissertations | Theses and Dissertations | | --- | --- | | Spring 5-5-2025
Data-driven Dynamic Decision-making Using Discrete Optimization and Supervised Machine Learning
Navid Rashedi
Thayer School of Engineering, [navid.rashedi.th@dartmouth.edu](navid.rashedi.th@dartmouth.edu)
Follow this and additional works at: [https://digitalcommons.dartmouth.edu/dissertations](https://digitalcommons.dartmouth.edu/dissertations)
Part of the Industrial Engineering Commons, Operational Research Commons, and the Other Engineering Science and Materials Commons | | Recommended Citation Rashedi, Navid, "Data-driven Dynamic Decision-making Using Discrete Optimization and Supervised Machine Learning" (2025) . Dartmouth College Ph. D Dissertations. 350. [https://digitalcommons.dartmouth.edu/dissertations/350](https://digitalcommons.dartmouth.edu/dissertations/350) This Thesis (Ph. D.) is brought to you for free and open access by the Theses and Dissertations at Dartmouth Digital Commons. It has been accepted for inclusion in Dartmouth College Ph. D Dissertations by an authorized administrator of Dartmouth Digital Commons. For more information, please contact [dartmouthdigitalcommons@groups.dartmouth.edu](dartmouthdigitalcommons@groups.dartmouth.edu). Data-driven Dynamic Decision-making Using Discrete Optimization and Supervised Machine Learning A Thesis Submitted to the Faculty in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Engineering Sciences by Navid Rashedi Thayer School of Engineering Guarini School of Graduate and Advanced Studies Dartmouth College Hanover, New Hampshire May 2025 Examining Committee: Chairman Vikrant Vaze Member Jonathan T. Elliott Member Eugene Santos Member Alexandre Jacquillat F. Jon Kull, Ph.D. Dean of Guarini School of Graduate and Advanced Studies Abstract In recent years, the operations research community has developed data-driven optimization techniques to solve complex combinatorial problems with the aid of machine learning. This thesis contributes to these efforts by combining machine learning with optimization to expedite online decision-making, with applications in transportation and healthcare. In the domain of airline operations recovery, the focus is on the aircraft recovery process—repairing disrupted schedules by minimizing overall disruption costs. Traditional exact methods are too time-consuming, while heuristic approaches often yield poor solution quality and lack generalizability across varying formulations. To address these challenges, this research employs supervised machine learning to identify near-optimal solution components by leveraging historical data. By integrating binary classification methods into a decision-aware framework, our approach prunes the decision space effectively, yielding high-quality solutions in significantly shorter runtimes than both exact and heuristic methods. In the healthcare domain, for the diagnosis of occult hemorrhage, we develop a datadriven framework that takes advantage of multisensor data and vital signs to detect internal bleeding early, particularly under capacity constraints. We conduct extensive experiments with animal and human data to engineer high-fidelity features and maximize predictive accuracy. Building on these predictions, we propose a decision-aware machine learning approach that dynamically updates patient risk scores over time and optimizes admissions to resource-intensive care units. Our method balances the trade-off between acting early (with less accurate information) versus waiting for more precise data, thus reducing both false positives and missed diagnoses. Through experiments based on data sets from our preclinical study, we show that our dynamic optimization framework surpasses traditional risk-based heuristics, leading to significantly improved pat

FAQs

How does the thesis improve online decision-making for combinatorial problems?

It combines supervised machine learning with decision-aware optimization to identify near-optimal components from historical data, pruning the decision space and accelerating online decisions.

What problem is addressed in the airline operations recovery application?

It focuses on aircraft recovery by repairing disrupted schedules through minimizing overall disruption costs, aiming to outperform slow exact methods and less generalizable heuristics.

How does the healthcare part handle occult hemorrhage diagnosis under capacity constraints?

It uses multisensor data and vital signs to detect internal bleeding early, then dynamically updates patient risk scores and optimizes admissions to resource-intensive care units while balancing early action versus waiting for more precise data.

Aug 3, 2026

Upload by Evangeline