From Bytes to Bites: Using Country Specific Machine Learning Models to Predict Famine

TL;DR

This study demonstrates that country-specific machine learning models, especially Random Forests, can effectively predict famine risks by analyzing diverse natural, economic, and conflict data, with accuracy varying across regions.

Contribution

It introduces a country-specific approach using machine learning models for famine prediction, emphasizing the importance of tailored models and comprehensive data collection.

Findings

Random Forest achieved 10.6% average prediction error.

Economic indicators are key predictors of household nutrition.

Prediction accuracy varies significantly across countries.

Abstract

Hunger crises are critical global issues affecting millions, particularly in low-income and developing countries. This research investigates how machine learning can be utilized to predict and inform decisions regarding famine and hunger crises. By leveraging a diverse set of variables (natural, economic, and conflict-related), three machine learning models (Linear Regression, XGBoost, and RandomForestRegressor) were employed to predict food consumption scores, a key indicator of household nutrition. The RandomForestRegressor emerged as the most accurate model, with an average prediction error of 10.6%, though accuracy varied significantly across countries, ranging from 2% to over 30%. Notably, economic indicators were consistently the most significant predictors of average household nutrition, while no single feature dominated across all regions, underscoring the necessity for comprehensive data collection and tailored, country-specific models. These findings highlight the potential of machine learning, particularly Random Forests, to enhance famine prediction, suggesting that continued research and improved data gathering are essential for more effective global hunger forecasting.