Many regions on earth everyday face limitations in the quantity and quality of available water resources. To that end, it is necessary to implement reliable methodologies for water consumption forecasting, that will lead to better management and planning of water resources. In this research, we analyse a first-time used large database containing data from 2 million water meters in 274 unique postal codes, in one of the most densely populated areas in Europe, which faces instances of droughts and overconsumption in hot summer
months. With the assistance of R programming language, we built and tested three alternative forecasting methodologies, employing univariate forecasting techniques including a machine-learning algorithm, with very promising results