Project

Predicting Global Healthcare Costs

Aggregated, cleaned, and formatted World Health Organization data on health care expense and non-communicable diseases.

Overview

Methods used: clustering, decision trees, support vector machines, niave Bayes, knn, and neural networks. Achieved accuracy up to 70% in predicting level of healthcare costs globally.

Client

Graduate school project, University of Colorado, Boulder.

My Role

Project Lead

Tools

Python

Dates

2023

"Digging through large datasets looking for value is the modern-day equivalent to prospecting for gold."

Copyright © 2025 Divi. All Rights Reserved.