Reports on a second energy predictor shootout contest to evaluate the most effective empirical or inverse regression models for modelling hourly whole-building energy baselines for purposes of measuring savings from energy conservation retrofits. The contest used two sets of measured hourly preretrofit and post-retrofit data from buildings participating in a revolving loan programme in Texas. The accuracy of the contestants' models was evaluated by determining their ability to predict data that were carefully removed from the training (or pre-retrofit) period. The savings predicted by the models were compared. Concludes that neural networks again provide the most accurate model of a building's energy use, although cleverly assembled statistical models appear to be as accurate, or in some cases more accurate, than some of the neural network entries.