Predictive Intelligence release notes
Summarize
Summarized using AI
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.
Summary of Predictive Intelligence release notes
The ServiceNow® Predictive Intelligence application, enhanced in the Zurich release, empowers you to create and train machine learning models to boost system performance, efficiency, and flexibility. This release introduces key improvements focused on error monitoring, advanced classification options, and data access validation to ensure smoother model training and operation.
Show less
Key Features
- Observability Dashboard and Error Logging: Prediction errors are now logged in a dedicated table, enabling the PI - Observability Dashboard to provide detailed analytics on prediction errors. This feature helps you proactively monitor and troubleshoot model performance issues.
- Advanced Classification Model Options: New customization parameters allow you to:
- Limit the model to the top N most frequent labels for more focused classification.
- Set minimum record thresholds for labels to be included during training, improving data quality.
- Remove "others" labeled records to reduce noise and enhance accuracy.
- Use the LightGBM algorithm for classification training, offering a powerful alternative for model building.
- Include JSON-formatted configuration parameters to fine-tune model training behavior.
- Data Access Validation: New validation logic verifies that data tables used in models have appropriate Access Control Lists (ACLs) granting Predictive Intelligence access, reducing training errors related to permissions.
- UI Enhancements: The Coral theme is now the default for portals, web, and mobile interfaces using Next Experience or Core UI, delivering a fresh, brand-neutral look. A dark theme option is also available to improve readability and reduce eye strain.
Key Outcomes
- You can efficiently monitor and analyze prediction errors to maintain high model reliability.
- Classification models can be precisely tailored to your data and business needs, improving prediction accuracy and relevance.
- Improved data access validation minimizes training failures caused by permission issues, streamlining model deployment.
- The updated UI themes enhance user experience across devices, supporting better engagement with Predictive Intelligence tools.
Additional Information
Predictive Intelligence is an AI Platform feature activated by default in ServiceNow. It integrates with related AI solutions like Document Intelligence and Task Intelligence to deliver comprehensive automation and machine learning capabilities across your organization.
The ServiceNow® Predictive Intelligence application enables you to create and train machine learning models to help improve the performance, efficiency, and flexibility of your systems. Predictive Intelligence was enhanced and updated in the Zurich release.
Predictive Intelligence highlights for the Zurich release
- Predictive Intelligence errors are logged in a new, dedicated table. The PI - Observability Dashboard leverages this table to provide analytics on prediction errors.
- New advanced options for Classification models are available, including new parameters and a new algorithm.
- Validation logic ensures that Predictive Intelligence models have ACLs to access data tables.
See Predictive Intelligence for more information.
New in the Zurich release
- Review any errors in predictions using the Observability Dashboard
- Monitor errors using the Observability Dashboard which provides analytics derived from a new table. This table is dedicated to logging any errors that may occur during Predictive Intelligence predictions.
- Leverage new advanced options for classification solutions
- Customize your classification models in Predictive Intelligence with the following advanced options.
- Configure include only top N labels: Limit the classification model to use only the top most frequent labels. You can choose a number as the limit.
- Minimum records needed for label to include it: Set a threshold for the minimum number of records a label must have in your dataset to be included in model training.
- Remove others label: Reduce noise in the model and enhance predictive accuracy by removing records with the label "others" from training data.
- Use LightGBM algo for classification model training: Enable the LightGBM (Light Gradient-Boosting Machine) algorithm for training classification models.
- Config parameters for model config in classification: Customize training behavior by including a dictionary of parameters in the JSON format.
UI changes
- Coral theme
- Coral is now the default theme for new portal, web, and mobile experiences with Next Experience or Core UI enabled. This theme provides a fresh look and feel, featuring brand-neutral illustrations to enhance your user experience. A dark theme option is available for web and mobile experiences.
Changed in this release
- Validation logic ensures that Predictive Intelligence can access data tables
- Reduce errors while training Predictive Intelligence models with the help of new validation logic. This validation checks whether your data tables have ACLs (Access Control Lists) granting access to Predictive Intelligence.
Activation information
Predictive Intelligence is a ServiceNow AI Platform feature that is active by default.
Accessibility information
- Dark theme
- The new Coral theme includes a dark theme option for web and mobile experiences. This option is commonly used to alleviate eye strain and improve readability.