Create a forecast model. This is the second step in the main PlanIQ activity flow.

After you've created the data collection (Stage 3, Step 1), you create a forecast model (Stage 3, Step 2). Forecast models use algorithms trained on information from data collections. 

To create a forecast model:

  1. In PlanIQ, select Forecast models.
  2. Select New forecast model in the upper right of the screen.
    The configuration dialog for Create a forecast model displays. 
  3. Enter your Forecast model name.
  4. Select a Data collection from the dropdown. 
  5. Select an Algorithm from the dropdown. The list populates based on your chosen data collection. The algorithm you select trains the forecast model (note: the default is Anaplan AutoML). Go to Algorithms to learn more.
  6. Beneath Forecast horizon, use the dropdowns.
      • To set the forecast frequency, select the Time interval
      • To set the length of the forecast, select How many intervals.

PlanIQ determines the interval and maximum forecast length. PlanIQ derives both the interval and length from the algorithm and the information from the data collection.

7. Beneath Additional settings, make the selections below (optional).

      • If the algorithm is either Anaplan AutoML or Amazon Ensemble, select an Optimization metric from the dropdown. Note: the default metric is MASE.  
      • Select from the Country-specific holiday calendar dropdown. This setting adds a related time series to the forecast model training. Country-specific holiday data is useful when the data collection represents data from a single country.
        Note: Make sure the algorithm applied supports related data.

8. Select Create forecast model. You can check the status in the Forecast models page.

Optionally, you can evaluate the forecast model before you create and run a forecast action. To evaluate:

    • Assess metrics in the inspector panel tab.
    • Import backtest data and compare the forecast against the actuals.