Differences Between Acquired and Live Datasets

In SAP Analytics Cloud you can use one of the following types of input datasets:

Acquired: Data is imported (copied) and stored in SAP Analytics Cloud. Changes made to the data in the source system don't affect the imported data.
Live: Data is stored in the source system. It isn't copied to SAP Analytics Cloud, so any changes in the source data are available immediately if no structural changes are brought to the table or SQL view.

When you select an input dataset to create a predictive model, you won't see any distinction between acquired and live datasets, although it is a good practice for the administrator creating the connection to a dataset to include "live" in the dataset name, or its description. You can also see live datasets in the list of objects available to you on the page Start of the navigation path Browse Next navigation step Files <User> End of the navigation path as they include (Live) in the file type.

There are some differences between the two types of input datasets that concern mainly the display of results in the predictive model debrief, and how some types of data are handled, when training or applying a predictive model. These differences will be resolved over time, as predictive models are improved with each release of SAP Analytics Cloud, but for the immediate future, please take into account the following differences that can be observed when using either an acquired or live input dataset:

Element	Acquired dataset	Live dataset
Support of data type conversion In the column Storage under Edit Variable Metadata, you can specify the data type for each variable.	Available If necessary, the physical data type, for example, a string, is automatically converted to the data type specified by the user, for example, a number.	Not available Note Training a predictive model won't complete if a user specified data type doesn’t match the physical data type.
Support of Model Publication to PAi When a predictive model has been successfully trained, the user has the ability to publish it to a PAi system.	Available. But you need the role Predictive Admin.	Not available The following message is displayed when the user clicks Publish “Sorry, publishing a predictive model trained using a live dataset, to a PAi application isn't supported. You can only publish predictive models that have been trained on acquired datasets.”

Element

Acquired dataset

Live dataset

Support of data type conversion

In the column Storage under Edit Variable Metadata, you can specify the data type for each variable.

Available

If necessary, the physical data type, for example, a string, is automatically converted to the data type specified by the user, for example, a number.

Not available

Note

Training a predictive model won't complete if a user specified data type doesn’t match the physical data type.

Support of Model Publication to PAi

When a predictive model has been successfully trained, the user has the ability to publish it to a PAi system.

Available. But you need the role Predictive Admin.

Not available

The following message is displayed when the user clicks Publish “Sorry, publishing a predictive model trained using a live dataset, to a PAi application isn't supported. You can only publish predictive models that have been trained on acquired datasets.”

Caution

The input datasets used to train and apply a predictive model must come from the same data source type. You can't apply a predictive model on a live dataset if it was trained with an acquired dataset, nor can you apply a predictive model on an acquired dataset if it was trained using a live one. However, you can have several predictive models trained and applied with live and acquired datasets in the same predictive scenario.

Note

While using live datasets, both live datasets (training and apply datasets) must come from the same SAP HANA system: you cannot train a predictive model with a live dataset with data from SAP HANA system 1 and then apply this predictive model on a live dataset with data coming from SAP HANA system 2.

The type of dataset you have used to train and apply your predictive model will impact the way you will consume the generated predictions in SAP Analytics Cloud. For more information, see Using the Generated Dataset in SAP Analytics Cloud.