You can add a forecast to a view when there is at least one date dimension and one measure in the view. If you’re interested in predictive modelling, also available in Tableau, see How Predictive Modelling Functions Work in Tableau.
To turn forecasting on, right-click (control-click on Mac) on the visualisation and choose Forecast >Show Forecast, or choose Analysis >Forecast >Show Forecast.
When no date dimension is present, you can add a forecast if there is a dimension field in the view that has integer values. For details, see Forecasting When No Date is in the View.
You can forecast quantitative time-series data using exponential smoothing models in Tableau Desktop. With exponential smoothing, recent observations are given relatively more weight than older observations. These models capture the evolving trend or seasonality of your data and extrapolate them into the future. Forecasting is fully automatic, yet configurable. Many forecast results can become fields in your visualisations.
When a forecast is showing, future values for the measure are shown next to the actual values.
Forecasting is not supported for Multidimensional data sources. In Tableau Desktop, multidimensional data sources are supported only in Windows.
You can publish a view that contains a forecast, and see the forecast when you view or edit the view on the web, but you cannot modify or add a forecast when you are editing a view on the web.
In addition, you cannot add a forecast to a view if it contains any of the following:
Grand Totals or Subtotals
Date values with aggregation set to Exact Date