Considering the constant growth of interest in energy efficiency in the building sector, it is necessary to apply and improve existing and also to develop new methods for prediction andanalysis of building energy consumption. In this paper cooling consumption of the model of a typical commercial building in Belgrade is analyzed. Detailed energy simulation is done usingsoftware HAP (Hourly Analysis Program). The influence of various building characteristics is investigated, and for creating building consumption database, three variables that most largelyaffect the cooling consumption are chosen: specific lighting power, window area and window shade coefficient. Those three parameters are varied and 245 simulations in total are used for creatingand testing the prediction models. The multiple linear model is created and the obtained equation is used for cooling consumption evaluation taking these three building parameters as input. Theartificial neural network and support vector machine (SVM) models are also developed for prediction and their results are compared with linear regression model. It has been shown that thestatistical methods, such are neural networks and support vector machines can achieve much higher accuracy in prediction than the linear regression model, gaining almost perfect match withsimulated values (mean absolute percentage error for testing the SVM model 0,26%)