Energy consumption modeling can provide various applications such as analyzing building's energy-related features and establishing baselines. It also serves as an important key tool to understand the energy efficient design requirement. Estimating building energy demand in a building is a challenging task, since it is depends on several parameters related to the building characteristics, equipment and systems, weather, occupants, and sociological factors. This paper describes the development of regression models, which are able to predict commercial building annual energy consumption in the early stages of the design. eQUEST and DOE-2 building simulation software programs were used to build and simulate individual building configuration that were generated using Monte-Carlo simulation technique. Ten thousand simulations for seven building shapes were performed to create comprehensive database covering the full ranges of design parameters. Several design parameters including building shape, materials and their thickness, and occupant schedule were considered in this study. The results of this study showed that the difference between regression-predicted and DOE-simulated annual building energy consumption are largely within 5%. It is envisioned that the developed regression models can be utilized to estimate the energy savings in the early stages of the design when different building schemes and design concepts are being considered.