Table of contents

Building and deploying models with Watson Machine Learning

Using IBM Watson Machine Learning, you can build analytical models and neural networks, trained with your own data. You can also deploy models, scripts, and functions, manage your deployments, and prepare your assets to put into production to generate predictions and insights.

Service This service is not available by default. An administrator must install this service on the IBM Cloud Pak for Data platform. To determine whether the service is installed, open the Services catalog and check whether the service is enabled.

This graphic illustrates a typical process for a machine learning model.

Building a Machine Learning model

Depending on what is installed and configured for your deployment, you can:

Using Watson Machine Learning in High Availability mode

By default, Watson Machine Learning is installed with a default scaling configuration of small, meaning the services run on a single pod. To configure Watson Machine Learning for a high availability option, where the service runs on two pods, the system administrator can use the scaling option for the installation script to change the configuration from small to medium.

Running Watson Machine Learning without IBM Watson Studio

Note: If Watson Studio is not installed, you will not be able to access any of the model-building tools and you will have to save your machine learning models to a deployment space programmatically. Additionally, you will be unable to create a batch deployment through the Analytic deployment space interface. Batch deployment requires that you upload a data asset from a project to a space to use as input for the deployment. Projects are not available without Watson Studio.