article · International Journal of Energy Research
Assessing energy poverty requires understanding complex socioeconomic dynamics that conventional statistical methods often struggle to capture. Machine learning ensemble models offer an alternative way to predict the multidimensional energy poverty index using socioeconomic data. Combining extreme gradient boosting with random forest yields high predictive accuracy, achieving strong correlation and low error rates. Other combinations, such as pairing extreme gradient boosting with multiple linear regression or artificial neural networks, demonstrate consistent generalisability and balanced predictive performance. Analysis reveals that key determinants of energy poverty include education levels alongside nutritional measures, specifically food consumption, household food insecurity access, and dietary diversity scores. These findings underscore a direct connection between energy vulnerability, educational attainment, and food security, offering analytical mechanisms to inform targeted socioeconomic and development policy interventions.
Energy poverty affects household well-being and economic development, yet its drivers are multifaceted. Demonstrating that food security metrics and education closely track energy poverty allows development agencies and governments to design integrated programmes. Machine learning tools can process complex socioeconomic data more accurately than traditional statistics, helping decision-makers pinpoint vulnerable populations and align social support interventions more effectively.
These predictive models represent applied and tested analytical tools suitable for integration into policy planning software, public sector monitoring platforms, or international development toolkits. Primary users include government ministries, development agencies, and non-governmental organisations working on poverty alleviation and energy access. However, translating these analytical ensembles into automated decision-support products requires further operational software development, data pipeline integration, and field deployment testing.
AI-generated from the published abstract. Always read the original work before citing.
This study aims to identify the key predictors of the multidimensional energy poverty index (MEPI) by employing advanced machine learning (ML) ensemble methods. Traditional energy poverty research often relies on conventional statistical techniques, which limits the understanding of complex socioeconomic factors. To address this gap, we propose an approach using three distinct ML ensemble models: extreme gradient boosting (XGBoost)‐random forest (RF), XGBoost‐multiple linear regression (MLR), and XGBoost‐artificial neural network (ANN). These models are applied to a comprehensive dataset encompassing various socioeconomic indicators. The findings demonstrate that the XGBoost‐RF ensemble achieves exceptional accuracy and reliability, with a root mean squared error (RMSE) of 0.041, an R ‐squared ( R 2 ) of 0.975, and a Pearson correlation coefficient of 0.992. The XGBoost‐MLR ensemble shows superior generalizability, maintaining a consistent R 2 of 0.845 across both the testing and training phases. The XGBoost‐ANN model balances complexity with predictive capability, achieving an RMSE of 0.056, an R 2 of 0.954 in the testing phase, and an R 2 of 0.799 in training. Significantly, the study identifies “Education,” “Food Consumption Score (FCS),” “Household Food Insecurity Access Scale (HFIA),” and “Dietary Diversity Score (DDS)” as critical predictors of MEPI. These results highlight the intricate relationship between energy poverty and factors related to food security and education. By integrating the insights from these ML models with policy initiatives, this study offers a promising new approach to addressing energy poverty. It highlights the importance of education, food security, and socioeconomic factors in crafting effective policy interventions.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1155/2024/9411326
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
