Domestic electricity usage estimation model using socio-economic factors

In this empirical study, socioeconomic factors that can easily be extracted from families have been used to build a "home electricity usage prediction" model based on two variables, family monthly income and size. Each of these was evaluated individually. Two machine learning models were built using those as features. Models are “Linear regression” “Random Forest” algorithms. This study revealed the such size very effective in domestic prediction building, where end usages not known. Furthermore, random forest algorithm found more for unseen data than linear regression algorithm. The accuracy further improved by adding into both models.