Prediction Studio provides data scientists with role-based authoring environment to facilitate configuration and management of AI and machine-learning resources for predictive, adaptive, and text analytics. From Prediction Studio, data scientists can also create and explore additional resources that are related to model development, such as data sets, taxonomies, and sentiment lexicons. Prediction Studio is available to users who specify pxPredictionStudio as one of the portals associated with their access group.
The following components are available in Prediction Studio:
The header at the top enables you to create models, search for the models that you already created, perform a number of maintenance tasks, or get help.
The navigation panel on the left provides quick access to the following work areas:
- In this work area, you can access, sort, and manage predictive, adaptive, and text analytics models within your application. By default, the models are displayed as tiles. Each model tile contains an icon for quick identification of model type, the model name, and the indication of whether the model is completed or being built.
- In this work area, you can perform a number of data exploration tasks, such as creating and managing data sets or viewing Interaction History summaries. In addition, you can access resources such as taxonomies or sentiment lexicons that provide features for building machine-learning models.
- This work area contains the global settings for model development, such as the internal database where model records and related resources are stored and their default application context.
This component appears at the bottom of Prediction Studio. From this toolbar, you can access advanced tools, such as Issues, Tracer, Live UI, Performance, and the Clipboard.