Rochester Institute of Technology
A Decision Support System for Global Vaccine Funding: Data-Driven Proposal Scoring, Epidemiological Risk Modeling, and Portfolio Optimization
Abstract
dc:description.abstractGlobal health financing must continually stretch limited immunization resources across competing priorities, and Gavi, the Vaccine Alliance, plays a central role in this landscape. This work reframes Gavi’s funding decisions as a multi-objective portfolio optimization problem that jointly considers health impact, equity, cost-effectiveness, sustainability, and epidemiological interdependence. To operationalize this approach, this study develops a decision support system grounded in Modern Portfolio Theory, treating each proposal as an asset characterized by expected return and risk. Proposal returns are estimated through a heterogeneous data-fusion pipeline that generates quantitative, multi-objective scores aligned with Gavi’s strategic priorities, while epidemiological risk is quantified using a novel agent-based network model that infers cross-country outbreak spillover via an epidemiological gravity mechanism. The integrated system, combining scoring, risk modeling, and portfolio optimization, was evaluated using a full factorial experimental design spanning 9 combinations of strategic priorities, initial disease burden, and budget. The risk-aware allocation approach achieved a median 1.31% (~242,000 fewer cases in the nominal 18.5M population) reduction in new infections, with improvements up to 15.15% under severe outbreaks, while maintaining near-complete budget utilization. These findings demonstrate that explicitly incorporating epidemiological interdependence into funding allocation offers more consistent, transparent, and epidemiologically foresighted recommendations, providing a scalable quantitative baseline to complement and strengthen expert review within Gavi’s decision-making process.
Degree
thesis:*- Name thesis:degree_name
- Artificial Intelligence (MS)
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Information Sciences and Technologies
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kumar, Ashutosh
- Contributors dc:contributor
-
- Ruben Proano
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.rit.edu/theses/12369