Applying a Time Series Model in SAP Analytics Cloud Smart Predict

Objectives

After completing this lesson, you will be able to:

  • Describe the steps to applying a time series model in Smart Predict

Apply a Time Series Model

Apply the Time Series Model

Once you have assessed the performance of your time series model and you want to apply it, save the predictive forecasts into a data set in three steps.

  1. From your model, select Save Forecast as highlighted in the image.Time series model with Save Forecast icon highlighted.
  2. In the Save Forecasts dialog, provide a name for your forecast. Save forecasts dialog.
  3. Select Save.

Find Your Generated Data set

To find your generated data set with the forecasts, you can either:

  1. From the side navigation, select Datasets then Recent Files.
  2. From the side navigation bar, select My Files.

Status

In the predictive model list, the status of your predictive model is updated to Applied.

Application Output Columns

The following columns are generated in the output data set when a time series model is applied:

NameDescription
ForecastIn this column, you find the forecast values for the target, based on the number of requested forecasts specified in the predictive model settings.
Error MinFor each requested forecast at a given horizon H, the predictive model calculates a confidence interval. The Error Min value is the lower bound of this confidence interval. It is equal to the forecasted value – sigma(RMSE)*1.96, where sigma (RMSE) represents the standard deviation of RMSE between the actual and forecasted target value at horizon H. The weighted value of 1.96 corresponds to a confidence level of 95%.
Error MaxFor each requested forecast at a given horizon H, the predictive model calculates a confidence interval. The Error Max value is the upper bound of this confidence interval. It is equal to the forecasted value + sigma(RMSE)*1.96, where sigma(RMSE) represents the standard deviation of RMSE between the actual and forecasted target value at horizon H. The weighted value of 1.96 corresponds to a confidence level of 95%.

In this table, you can see an example of the newly added columns:

Forecast data with Forecast, Error Min and Error Max added to it.

Log in to track your progress & complete quizzes