This study utilises a rich UK dataset of smart demand metering data, household 10 characteristics, and weather data to develop a demand forecasting methodology that combines 11 the high accuracy of machine learning models with the transparency of regression methods. 12 For this reason, a Random Forest model is used to predict daily demands one day ahead for groups of properties (mean of 3.8 households/group) with homogenous characteristics. A variety of interpretable machine learning techniques (variable permutation, Accumulated Local Effects plots -ALE, Individual Conditional Expectation curves -ICE) are used to quantify the influence of these predictors (temporal, weather, and household characteristics) on water consumption. Results show that when past consumption data are available, they are the most important explanatory factor. However, when they are not, a combination of household and temporal characteristics can be used to produce a credible model with similar forecasting accuracy. Weather input has overall a mild to no effect on the model's output, although this effect can become significant under certain conditions.