Population ageing is becoming a key social issue in recent decades, particularly in Western countries, where this fact, together with the increase of life expectancy, has posed a significant strain on public finances and health services. In this context, many technological developments are often proposed to promote and support the independent living of elderly at their own homes, thus avoiding or postponing possible entries into social residences. Among them, smart meters provide a nonintrusive way to monitor and estimate the tenants’ daily activities, by only using a single-point measurement in the mains at the entrance of the household. This work describes a regression approach to estimate the energy consumption of a house by means of a LSTM neural network. For that purpose, a pilot has been run on a house during six months in order to collect the electrical data, which will be used later to train the neural network. After that training, the network tries to estimate the energy consumption every 15 minutes, so any deviation between the predicted sample and the measured one might be used to detect anomalies in the daily routine of the tenant.