Georgia Institute of Technology
Operationalization of AI Systems Through Data-Centric Design
Abstract
dc:description.abstractThis dissertation investigates how artificial intelligence systems can be operationalized through data-centric design so as to remain reliable, interpretable, and operationally meaningful in real decision environments. It advances this thesis through three research streams: data-centric AI systems across the application domains of public health and personalized medicine, and foundational data science for AI systems. Across these streams, the dissertation introduces new methodologies that integrate prediction, optimization, and action in the presence of delayed reporting, incomplete observations, local data limitations, and distributional instability. Collectively, this work argues that the operationalization of AI is fundamentally a data-centric design problem.
Degree
thesis:*- Name thesis:degree_name
- Machine Learning, PhD
- Department thesis:degree_department
- Industrial and Systems Engineering
- Grantor
- Georgia Institute of Technology
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Liao, Che-Yi
- Advisor dc:contributor.advisor
-
- Paynabar, Kamran
- Committee members dc:contributor.committeemember
-
- Garcia, Gian-Gabriel
- Xie, Yao
- Li, Jing
- Keyvanshokooh, Esmaeil
- ORCID person:identifier.orcid
Rights
- Language dc:language.iso
- English
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/81777