Data-Driven Socioeconomic Segmentation for Residential Energy Planning: A Machine Learning Approach.
Saved in:
| Title: | Data-Driven Socioeconomic Segmentation for Residential Energy Planning: A Machine Learning Approach. |
|---|---|
| Authors: | Ferreira, Lucas Camaz1 (AUTHOR), Leite Coelho da Silva, Felipe1,2 (AUTHOR), da Silva Cordeiro, Josiane1 (AUTHOR), López-Gonzales, Javier Linkolk2 (AUTHOR), Tocto-Cano, Esteban2 (AUTHOR), Centurion, Lennin2 (AUTHOR) lenin.centurion@upeu.edu.pe |
| Source: | Energies (19961073). May2026, Vol. 19 Issue 9, p2229. 19p. |
| Subject Terms: | *Socioeconomics, *Machine learning, *Energy consumption, *Decision trees, *Home energy use, *Artificial neural networks |
| Abstract: | The Brazilian residential sector is one of the largest consumers of electricity, making residential energy consumption a critical component of national energy systems. Electricity consumption patterns in this sector are closely associated with household appliance ownership and, consequently, with socioeconomic status. For residential energy planning to operate more equitably and efficiently, it is essential that consumption analyses be aligned with the socioeconomic conditions of the population. This study examines the role of socioeconomic variables in residential energy planning through the application of supervised machine learning algorithms within a data-driven socioeconomic segmentation framework. Decision trees, support vector machines, and artificial neural networks were implemented using data from the Brazilian residential sector to evaluate model performance and to determine the extent to which household socioeconomic status can be inferred from variables related to appliance ownership and electricity consumption characteristics. The results showed that household appliances, such as refrigerators, microwave ovens, and air conditioners, exhibited substantial predictive power in relation to socioeconomic status, thus improving the interpretation and understanding of residential energy consumption from a multidimensional perspective. The neural network model achieved the highest predictive performance. By enabling data-driven socioeconomic segmentation based on observable electricity consumption patterns, this approach provides relevant insights for residential energy planning and contributes to more targeted and equitable energy policy design, supporting Sustainable Development Goal 7 on Affordable and Clean Energy and Sustainable Development Goal 10 on Reduced Inequalities. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | The Brazilian residential sector is one of the largest consumers of electricity, making residential energy consumption a critical component of national energy systems. Electricity consumption patterns in this sector are closely associated with household appliance ownership and, consequently, with socioeconomic status. For residential energy planning to operate more equitably and efficiently, it is essential that consumption analyses be aligned with the socioeconomic conditions of the population. This study examines the role of socioeconomic variables in residential energy planning through the application of supervised machine learning algorithms within a data-driven socioeconomic segmentation framework. Decision trees, support vector machines, and artificial neural networks were implemented using data from the Brazilian residential sector to evaluate model performance and to determine the extent to which household socioeconomic status can be inferred from variables related to appliance ownership and electricity consumption characteristics. The results showed that household appliances, such as refrigerators, microwave ovens, and air conditioners, exhibited substantial predictive power in relation to socioeconomic status, thus improving the interpretation and understanding of residential energy consumption from a multidimensional perspective. The neural network model achieved the highest predictive performance. By enabling data-driven socioeconomic segmentation based on observable electricity consumption patterns, this approach provides relevant insights for residential energy planning and contributes to more targeted and equitable energy policy design, supporting Sustainable Development Goal 7 on Affordable and Clean Energy and Sustainable Development Goal 10 on Reduced Inequalities. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 19961073 |
| DOI: | 10.3390/en19092229 |
