Use of Boosting Algorithms in Household-Level Poverty Measurement: A Machine Learning Approach to Predict and Classify Household Wealth Quintiles in the Philippines

TL;DR

This paper evaluates various boosting algorithms for predicting household poverty levels in the Philippines, finding CatBoost to be the most accurate and efficient model for classifying household wealth quintiles.

Contribution

It introduces a comparative analysis of five boosting algorithms for household poverty prediction, highlighting CatBoost's superior performance and computational efficiency.

Findings

CatBoost achieved 91% accuracy in poverty classification.

XGBoost and GBM closely followed with 89% and 88% accuracy.

CatBoost demonstrated high testing efficiency despite longer training times.

Abstract

This study assessed the effectiveness of machine learning models in predicting poverty levels in the Philippines using five boosting algorithms: Adaptive Boosting (AdaBoost), CatBoosting (CatBoost), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LightGBM), and Extreme Gradient Boosting (XGBoost). CatBoost emerged as the superior model and achieved the highest scores across accuracy, precision, recall, and F1-score at 91 percent, while XGBoost and GBM followed closely with 89 percent and 88 percent respectively. Additionally, the research examined the computational efficiency of these models to analyze the balance between training time, testing speed, and model size factors crucial for real-world applications. Despite its longer training duration, CatBoost demonstrated high testing efficiency. These results indicate that machine learning can aid in poverty prediction and in the development of targeted policy interventions. Future studies should focus on incorporating a wider variety of data to enhance the predictive accuracy and policy utility of these models.