 This paper compared three different machine learning algorithms, medium-neural networks, MNN, whale optimization algorithm, WAO, and support vector machine, SVM, to estimate electricity demand for Turkey's mainland. The results showed that MNN had the lowest root mean square error, RMSE, and mean absolute error, MAE, of 5.325 times 10 to the power of negative 14 and 28.35 respectively. Additionally, the correlation coefficient between the estimated and actual data was highest for MNN at 0.976. This article was authored by Mustafa Saglam, Catalina Spattaru, and Omar Ali Karaman.