Application Of Machine Learning Approach In Hotel Energy Consumption Analysis

Energy usage in the hotel industry is an important concern, affecting both operating costs and the sustainability of the environment conventional approaches to energy regulation frequently deficiency the precision essential for optimal competence. One common drawback in this field is the inadequate efficiency in forecasting energy usage patterns due to the difficulty of influencing aspects. This study addresses these issues by applying a Monarch Butterfly Optimizer-driven Enhanced Ada Boost (MBO-EAB) technique, which improves prediction accuracy and enhances energy consumption more efficiently than traditional approaches. The hotel energy consumption measurement dataset was employed and min-max normalization used for preprocessing. The study was executed through Python software. Results establish that MBO-EAB significantly superiors Enhanced AdaBoost, attaining a coefficient of determination (R2)(0.92) and a mean squared error (MSE) (2.1). These outcomes highlight the significance of MBO-EAB in enhancing energy usage predictions and raising energy regulations in hotels.