Forecasting in Tableau
Forecasting is the process of making a prediction of the future based on past and present data and most commonly achieved by analysis of trends.
Forecasting in Tableau uses a technique called exponential smoothing. Exponential smoothing models capture the evolving trend or seasonality of the data and extrapolate them into the future. In other words, forecast algorithms in Tableau try to find a regular pattern in measures that can be continued into the future.
Structures that support creating a Forecast:
The field you want to forecast (Sales) is on the Rows shelf and a continuous date field (Week) is on the Columns shelf or vice versa.
The arrow on the right side of the SUM(Sales) pill indicates the field being forecasted.
The field you want to forecast is on either the Rows or Columns shelf, and discrete dates are on either the Rows or Columns shelf. At least one of the included date levels must be Year.
The field you want to forecast is on the Marks card, and a continuous date or discrete date set is on Rows, Columns or Marks.
This shows a sales prediction in 2019 based on previous years.
Adding a Forecast in Tableau
For example, if you want to visualise estimated future values of the measure Sales in addition to actual historical values:
1. Bring Order Date to the Columns shelf, then drill down to month and convert month to a continuous measure.
2. Next, bring Sales to the Rows shelf.
3. This creates a line chart showing the sales over time.
4. Click on the analytics tab and drag and drop forecast to view.
5. The estimated values are shown by default in a lighter shade of the colour used for the historical data:
5. The colour of the forecast can be changed on the view to make it stand out:
Forecasting can be used in business as a decision-making tool to help in budgeting, planning and estimating future growth. In other words, forecasting is an attempt to predict future outcomes based on previous information.