inputting baseline facility condition data to a neural network model generator, the baseline facility condition data representing baseline facility conditions during a first time interval before energy conservation measures and comprising weather conditions experienced by the facility during the time interval;

inputting baseline energy consumed by the facility during the first time interval;

the neural network model generator generating a neural network model in response to the baseline facility condition data and baseline energy consumed, the neural network model modeling how facility energy consumption responds to facility conditions;

inputting actual facility condition data to the neural network model, the actual facility condition data representing actual facility conditions during a second time interval after the energy conservation measures and comprising weather conditions experienced during the second time interval;

inputting actual energy consumed by the facility during the second time interval;

the neural network model outputting, in response to the actual facility condition data, an estimate of energy that would have been consumed under the baseline facility conditions but for the energy conservation measures;

computing energy savings, wherein the energy savings are defined by a difference between the actual energy consumed during the second time interval and the estimate of energy that would have been consumed but for the energy conservation measures; and

generating Energy Efficiency Certificates (EECs) corresponding to the computed energy savings.