Introduction to Machine Learning
Machine Learning
extracts key characteristics, patterns, and anomalies from your historical data to create predictive
models. These models then contain insights from your data that you can transform into actions and
business decisions. Your company's historical data contains information that can improve your
business decisions.
By integrating Machine Learning models into Operational Decision Manager decision services, you can apply predictive insights from historical data and prescriptive business decisions based on company policies.
Machine Learning models are built with IBM Watson® Machine Learning, which is part of IBM® watsonx.ai™. Watson Machine Learning provides a full range of tools to build, train, and deploy Machine Learning models. You can choose the tool with the level of automation or autonomy that matches your needs.
Watson Machine Learning provides the following tools:
- AutoAI experiment builder for automatically processing structured data to generate model-candidate pipelines. The best-performing pipelines can be saved as a machine learning model and deployed for scoring.
- Deployment spaces give you the tools to view and manage model deployments.
- Tools to view and manage model deployments.
For more information, see Watson Machine Learning on IBM watsonx™
.
Setup and usage
The following sections cover the setup and usage of Machine Learning.
| Activity | Description | Information |
|---|---|---|
| Applying | This example takes you through the process of adding a Machine Learning model to a decision service. You use the Miniloan sample decision service and the Machine Learning Mortgage Approval Prediction Model. | Applying a Machine Learning model |
| Configuring | You create an ml.properties file with the required Machine Learning service configuration and set it as a XOM resource. This approach offers the advantage of defining the endpoint for each RuleApp, enhancing customization and flexibility in managing Machine Learning configurations. It can be done by using Rule Designer, the Rule Execution Server console or REST API. | Adding a Machine Learning configuration file as a XOM resource |
| Updating | You can update the deployment IDs or provide an updated JSON of YAML file to alter the input and output fields. | Updating Machine Learning references |
| Deleting | You can delete Machine Learning enhancements that you no longer want to use. | Deleting Machine Learning references |
| Return codes | When you do a Machine Learning call from Operational Decision Manager, you are returned the output values and an integer return code. | Machine Learning return codes |
| Model export | You can use a script as an alternative to run the process to export a model from Machine Learning. | Scripts to export Machine Learning models return codes |