Smart meters installed at the user-level provides a new data source for managing water infrastructure. This research explores the use of machine learning methods to forecast hourly water demand using smart meter data at the user-level. Random Forests (RF), Artificial Neural Network (ANN), and Support Vector Regression (SVR) are applied to forecast demand using predictors that include lagged demand, seasonality, weather, and household characteristics. Time-series clustering is applied to differentiate the time of day and days of the week, which improves model performance. Two modeling approaches are compared. Individual models are developed separately for each smart meter, and a group model is trained using a dataset of multiple meters. The approaches perform similarly well. Individual models predict demands at specific meters with lower error, while the group model predicts demands at new meters with lower error. Results demonstrate that RF and ANN perform better than SVR across all scenarios.