Investigating the relationship between nominal GDP and adult HIV/AIDS prevalence using machine learning methods

Abstract

PURPOSE: The aim of this article is to analyze and model the relationship between nominal gross domestic product (GDP) and adult HIV/AIDS prevalence by machine learning methods.

DESIGN/METHODOLOGY/APPROACH: The study utilized publicly available GDP and adult HIV/AIDS prevalence data. To achieve the research objective, machine learning and statistical regression models were used.

FINDINGS: Using machine learning models and methods, it is possible to model the relationship between nominal GDP and adult HIV/AIDS prevalence. Selected indicators examining the differences between actual and predicted values indicated the best fit for the Ensemble Boosted Trees model. The relationship between nominal GDP and adult HIV/AIDS prevalence is negative and statistically significant.

PRACTICAL IMPLICATIONS: Possibilities of modeling adult HIV/AIDS prevalence and nominal GDP using machine learning models and methods.

ORIGINALITY/VALUE: This article makes a significant contribution to the development of knowledge on the relationship between nominal GDP and adult HIV/AIDS prevalence. Furthermore, it demonstrates the feasibility of using machine learning methods to model this relationship.