English

Using Machine Learning to Predict Poverty Status in Costa Rican Households

Applications 2021-11-29 v1

Abstract

This study presents two supervised multiclassification machine learning models to predict the poverty status of Costa Rican households as a way to support government and business sectors make decisions in a rapidly changing social and economic environment. Using the Costa Rican household dataset collected via the proxy means test conducted by the Inter-American Development Bank, Random Forest and Gradient Boosted Trees achieved F1 scores of 64.9% and 68.4%, respectively. This study also reveals that education has the greatest impact on predicting poverty status.

Cite

@article{arxiv.2111.13319,
  title  = {Using Machine Learning to Predict Poverty Status in Costa Rican Households},
  author = {Ji Yoon Kim},
  journal= {arXiv preprint arXiv:2111.13319},
  year   = {2021}
}
R2 v1 2026-06-24T07:52:39.562Z