Enhancing Household Energy Consumption Forecasting Using the
XGBoost Algorithm with Cross-Validation and Residual-Based Evaluation
Dublin Core
Title
Enhancing Household Energy Consumption Forecasting Using the
XGBoost Algorithm with Cross-Validation and Residual-Based Evaluation
XGBoost Algorithm with Cross-Validation and Residual-Based Evaluation
Subject
XGBoost, Energy Forecasting, Cross-Validation, Residual Analysis, Machine Learning, Sustainability
Description
Accurate forecasting of household energy consumption plays a crucial role in optimizing energy efficiency, supporting sustainable policy
decisions, and improving operational management in smart grid systems. This study enhances conventional XGBoost-based forecasting by
integrating cross-validation and residual-based evaluation to ensure model robustness and interpretability. Using a dataset of over 90,000 daily
household energy records that include temperature, humidity, and appliance-level usage, a systematic preprocessing pipeline was applied—
comprising data cleaning, normalization, temporal feature transformation, and partitioning into training and testing subsets. The proposed model
was trained using 10-fold cross-validation to minimize overfitting and validated through residual error analysis to assess stability and bias.
Evaluation metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the coefficient of determination (R²),
demonstrate superior predictive accuracy, achieving MAE = 0.48, RMSE = 0.64, and R² = 0.9864. Visualization of actual versus predicted
consumption and symmetric residual distribution further confirm the model’s reliability. The findings highlight that the enhanced XGBoost model
not only achieves high precision but also provides a robust foundation for real-time energy monitoring, anomaly detection, and sustainable
household energy management. Future work will integrate SHAP-based interpretability and comparative benchmarking with deep learning
approaches.
decisions, and improving operational management in smart grid systems. This study enhances conventional XGBoost-based forecasting by
integrating cross-validation and residual-based evaluation to ensure model robustness and interpretability. Using a dataset of over 90,000 daily
household energy records that include temperature, humidity, and appliance-level usage, a systematic preprocessing pipeline was applied—
comprising data cleaning, normalization, temporal feature transformation, and partitioning into training and testing subsets. The proposed model
was trained using 10-fold cross-validation to minimize overfitting and validated through residual error analysis to assess stability and bias.
Evaluation metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the coefficient of determination (R²),
demonstrate superior predictive accuracy, achieving MAE = 0.48, RMSE = 0.64, and R² = 0.9864. Visualization of actual versus predicted
consumption and symmetric residual distribution further confirm the model’s reliability. The findings highlight that the enhanced XGBoost model
not only achieves high precision but also provides a robust foundation for real-time energy monitoring, anomaly detection, and sustainable
household energy management. Future work will integrate SHAP-based interpretability and comparative benchmarking with deep learning
approaches.
Creator
Dwi Sugianto1,*, Koko Edy Yulianto2
Source
https://ijiis.org/index.php/IJIIS/article/view/253/161
Publisher
Amikom Purwokerto University
Date
march 2025
Contributor
Fajar bagus W
Format
PDF
Language
English
Type
Text
Files
Collection
Citation
Dwi Sugianto1,*, Koko Edy Yulianto2
, “Enhancing Household Energy Consumption Forecasting Using the
XGBoost Algorithm with Cross-Validation and Residual-Based Evaluation,” Repository Horizon University Indonesia, accessed January 1, 2026, https://repository.horizon.ac.id/items/show/9729.
XGBoost Algorithm with Cross-Validation and Residual-Based Evaluation,” Repository Horizon University Indonesia, accessed January 1, 2026, https://repository.horizon.ac.id/items/show/9729.