Application of Machine Learning Models on Individual Household Electric Power Consumption

This paper presents research on the application of various machine learning models to predict power consumption usage within a household. The models used for prediction are Decision Tree Regressor, Random Forest Regressor, Extra Trees Regressor, XGBoost Regressor, and K Nearest Neighbors Regressor. Mean Absolute Error, Root Mean Square Error, and Coefficient of Determination are evaluated as different performance matrices to know the best model that can be used for prediction in this application. The results show that the XGBoost regressor outperforms the other models.