The increase in electricity consumption has negative effects on the environment, including greenhouse gas emissions, global warming, and rapid climate change. In an attempt to address this global problem, this research aims at developing machine learning models for the prediction of electricity consumption in hotels. The models are implemented using several techniques, including K-nearest neighbors, radial basis neural network, support vector machines, decision tree, and Gaussian process. The performance of the aforementioned models is evaluated by measuring the mean absolute error, mean absolute percentage error and root-mean squared error using split validation. Finally, two-tailed Student's t-tests are performed to evaluate the statistical significance level of prediction models. The results demonstrate that the K-nearest neighbors model accomplished the highest prediction performance yielding mean absolute error, mean absolute percentage error and root-mean squared error of 130.77, 276.45 and 4.79%, respectively. Support vector machines provided the lowest prediction accuracy accomplishing mean absolute error, mean absolute percentage error and root-mean squared error of 303.39, 382.78 and 11.98%, respectively.