Defining the Settings of Time Series Predictive Model With a Planning Model as Data Source

Before you train your Time Series predictive model using a planning model as data source, you need to specify how you want your predictive model to be trained through the Settings panel.

The following sections mirror the sections of the Settings pane you need to complete to create your predictive model.

For more information about what is currently supported in Smart Predict, see the section Restrictions Using Planning Model as Data Source for Smart Predict in Restrictions.

General

Settings	Action	Additional Information
Description	Enter what your predictive model is trying to do.	For example, forecast product sales by city.
Times Series Data Source	Browse and select the planning model you want to use as data source.	Smart Predict supports only standalone planning models. BPC planning models are not supported whether these are live or acquired..
Version	Browse and select the planning model version you want to use as data source.	The input version must be a public version, not in edit mode, or a private version. You have a least read access to it. There are also some specificities when currency conversion is enabled. See How does Smart Predict Support Currencies Defined in Planning Model?.

Predictive Goal

Settings	Action	Additional Information
Signal	Select the measure you want to get predictive forecasts for.	A valid measure is a measure that is data entry enabled. If you select a non-supported measure, an error with be raised at training time or when writing-back the predictive forecasts. For more information, see the section Restrictions Using Planning Model as Data Source for Smart Predict in Restrictions. If your signal is related to a currency, you also have the option to select Default Currency or Local Currency. The option you choose determines the currency used to forecast and report on your signal. For more information, see the chapter How does Smart Predict Support Currencies Defined in Planning Model?
Date	The date dimension in the predictive model.
Time Granularity	By default, it's the level of date granularity available in the planning model data source.	If the lowest level of the date hierarchy in the planning model is daily, then Smart Predict will create daily predictive forecasts.
Number Of Forecasts	Select the number of predictive forecasts you want.	For more information, see How Many Forecasts can be Requested?
Entity	Select up to five dimensions or attributes for which you want to get distinct forecasts. This field is optional.	This corresponds to defining each entity that you want to get forecasts for. The predictive model will capture specific behaviors for each entity and will generate distinct predictive forecasts. For more information, see How Can You Get Distinct Predictive Forecasts per Entities For Your Planning Model? Note There are specific restrictions on entities. For more detailed information, see the section Restrictions Using Planning Model as Data Source for Smart Predict in Restrictions.

Predictive Model Training

Settings	Action	Additional Information
Train Using	Select whether you want to train your predictive model using all observations or a window of observation. If you choose to use a window of observations you'll need to specify the size of the window you want to use. Note If the range of predictive forecasts overlaps existing data in the private version, data will be overriden.	It can be useful to define the range of observations that will be used to train the predictive model. You may want to ignore very old observations or inappropriate observation to avoid that your predictive model learns based on obsolete/inappropriate behavior. Example For example, if you want to forecast travel costs for next year, you might want to ignore a couple of months in your past data where travel has been frozen for budget reasons.
Until	Select whether you want to train your predictive model until the last observation or another date of your choice.	If you select a custom observation date, make sure it stays within the time range defined in the data source planning model.
Force Positive Forecasts	Switch the toggle on if you want to get positive forecasts only.	This turns negative predictive forecasts to zero. This can be useful when predictive forecasts only make sense as positive predictive forecasts. For example, if you need to forecast the number of sales for one of your main product by major cities for a region. It makes no sense to get negative values. Either you sell a number of products or you sell none of them. Negative values will be turned to 0.

Click Train & Forecast button. Thanks to the generated reports, you can analyze the predictive model performance and decide if you need to further refine your predictive model or if you can use the predictive forecasts with confidence. For more information, see Analyzing the Results of Your Time Series Predictive Model.