Surrogate modeling is a technique to approximate thebehavior of complex systems based on a limited set ofcomputationally expensive simulations. Such modelscan permit real time optimization of building designs.There are many ways to develop the surrogate modelhowever, the relative advantages and disadvantages ofone modeling technique versus another are not wellunderstand, so modelers lack a criteria for selectingamongst approaches. The objective of this paper is tocompare the accuracy and computation time of multiplemethods. This paper also explores the choice of designvariables and parameter combinations to estimate thebuilding energy consumption when climate is one of thevariables. The results of this analysis will contribute toselecting a regression technique that limits errorsrelative to a detailed simulation.