Calculates or predicts a future value based on a trained and deployed forecasting model. In any forecasting model such as AXCEL.FORECAST.ARIMA or AXCEL.FORECAST.ETS, the user can select a deployment name that is used in this function. By using this function, the process of training and building the model is separated from deployment which provides security, consistency, and integration. The predicted value is a continuation of historical values. You can use this function to predict sales, revenue, inventory, or consumer trends.
AXCEL.FORECAST.RUN(deployment, forecast, [predictors], [version], [owner], [plot])
The AXCEL.FORECAST.RUN function syntax has the following arguments:
deployment Required. This is the same “deployment” name used in the execution of one of AXCEL.FORECAST models. Please note that this name is case sensitive.
forecast Required. The number of time steps that the user wants to forecast from the last data point in training data. For instance, if the data used for training is monthly from January 2000 to March 2001 and the forecast is set to 6, the function provides a 6-month forecast starting from April 2001 to September 2001.
predictors Optional. If you have additional predictors in the deployed model, such as the unemployment rate, the user should provide the predictor for forecasting. Please note that all predictors should have the same order in columns as used in the training datasets.
version Optional. This is the version of the deployment you’d like to run. If it is not identified, Axcel runs the latest version of the deployment.
owner Optional. The default is the user running the function. If you are not the owner of the model, you should provide the username of the model owner. Depends on the tier of the owner’s subscription, they may restrict access to the model to a list of authorized users.
plot Optional. The default is FALSE. If you would like to have a visualization of the forecast, you should set it to TRUE.
when you type =AXCEL.FORECAST.RUN in an Excel cell, the IntelliSense guides you through required and optional (shown in  brackets) inputs:
In the example above, we have:
=AXCEL.FORECAST.RUN(“test-arima”, 6,,”admin”, TRUE)
This means that the name of the model is test-arima, we would like to have 6 periods (in this case is a month) forecast, we do not have predictors, the model owner is admin and we would visualize the forecast. Executing this function results in a table of forecasts and a graph as presented below:
As shown, forecasts are reported in the workbook. The first column is the date index, the second column is the forecast. Axcel also reports the forecast with 80% and 95% confidence to help the process of decision making.
FORECAST.RUN does not send any content to the console.