Integrating Location Data into Analytics: Methods, Applications, and Fairness in Public Healthcare
Graduation Year
2024
Document Type
Dissertation
Degree
Ph.D.
Degree Name
Doctor of Philosophy (Ph.D.)
Degree Granting Department
Business Administration
Major Professor
Balaji Padmanabhan, Ph.D.
Co-Major Professor
Kaushik Dutta, Ph.D.
Committee Member
Wolfgang Jank, Ph.D.
Committee Member
Mohammadreza Ebrahimi, Ph.D.
Committee Member
Anand Kumar, Ph.D.
Keywords
AI Bias, Data-driven Forecasting, Epidemic Spread, Health Equity, Population Mobility, Social Vulnerability
Abstract
This dissertation explores the application of location data in healthcare management, focusing on epidemic spread forecasts and fairness in healthcare access. It demonstrates the power of location data in understanding and forecasting epidemic spread with two examples, using mobility metrics derived from the location data. The second example also considers the effect of social vulnerability along with population mobility and extends a popular deep-learning algorithm to accept static anddynamic data. The dissertation also proposes health equity measures by evaluating the alignment between healthcare facility locations and people’s mobility patterns, considering demographic factors. This research highlights the valuable insight location data can provide in healthcare and offers practical implications for decision-makers.
Scholar Commons Citation
Ray, Arindam, "Integrating Location Data into Analytics: Methods, Applications, and Fairness in Public Healthcare" (2024). USF Tampa Graduate Theses and Dissertations.
https://digitalcommons.usf.edu/etd/11149
