TARGETED ENERGY USAGE DEVICE PRESENCE DETECTION USING MULTIPLE TRAINED MACHINE LEARNING MODELS

Abstract

Embodiments generate machine learning predictions to discover targeted device energy usage. Embodiments train a first machine learning model to predict a presence of a first device, where a training data used to train the first machine is deficient for a second device. Embodiments train a second machine learning model to predict a presence of a second device. Embodiments receive input data of household energy use and weather data and, based on the input data, use the trained first machine learning model to predict the presence of the first device per household. Based on the input data, embodiments use the trained second machine learning model to predict the presence of the second device per household. Embodiments then subtract the households predicted to have the second device from the households predicted to have the first device to generate a prediction of households that have the first device.

Documents