1.2 New Features in This Release

The following new features are incorporated in this release CS 8.1.3.0.0.

ML4AML
  • Automated Scenario Calibration
    • Cloning functionality: Users can replicate the notebooks that have been developed or run in one folder in any number of folders. This will allow the user to replicate the analysis carried out on one segment of data across other segments with minimal effort.
    • ATL/BTL Partitioning: Users can partition tuning events generated by applying thresholds to tunable parameters. This allows users to easily create ATL/BTL populations for analysis without re-executing the scenarios.
    • Scenario Conversion Utility Verification: Consistency between alerts generated by ASC and core Behavior Detection can now be validated across multiple threshold sets. This will allow customers to more quickly validate ASC scenario execution for a wide range of threshold sets.
  • Behavioral Models
    • Feature Contributions for Non-Alerted Entities: Feature contributions for non-alerted entities are now tracked to support better risk management. Users can now better understand why any specific entity was not alerted.
    • Utilize Labels from Scenarios with Differing Lookbacks: A mechanism has been provided that allows users to create models from scenarios which do not have identical lookbacks or frequencies. This will allow customers to consolidate similar scenarios into a model even when these scenarios ran with varying lookbacks and frequencies.
    • New Base Features: New base features and red flag features have been added that cover a greater breadth of risks allowing customers to build behavioral models for a wider range of risks.
Model Pipelines
  • Model Review: New screen to do peer-review for Drafts of Model Pipelines. Allows developers to review and received feedback on various aspects like Conceptual Soundness, Data Quality, Implementation Testing and Model Governance Assessment. These are admin-configurable and will allow for introduction of custom review types.

    Reviewers can also Clone the Drafts and update/execute to do validations on their own copy.

  • Private Credential Injection: Allows individual users to optionally use their private credentials (without saving them in the system) for database connections. If not provided, connections will fall back to services accounts that is configured in Data Stores.
  • Upper limit for Python memory consumption can now be enforced for Model Pipeline executions.
  • Stage-level view is now available in Pipeline Canvas for enhanced navigation.
  • Executions can now also be done at stage-level.
  • Session Management: Allows users to create, manage and choose the runtime sessions. Runtime sessions are now synced between Pipeline Canvas and Notebook view.
  • Git Integration: Configured Git URLs now show as drop-down for selection.
  • Tags can now optionally be provided during Model Publish.
  • Draft visibility can now also be restricted to private and shared with selected users and user-groups.
  • Users can now directly create new sets from within Parameter Sets user interface.
  • Dashboard outputs are now specific to logged-in user.
Workspace
  • A new details screen has been introduced for comprehensive overview of workspace details and for simplified updates of workspace definition.
  • Support for Materialized Views and Triggers in Data Sourcing.
  • Workspace creation, which can take several minutes, has now been made as a background process. Workspace cards will now appear even for ongoing and failed creation processes.
  • Object dependencies can now also be optionally included during metadata sourcing/migration.
Utilities
  • New shell script utility to perform sync up of workspace schema with Data Model as an offline process.
  • Scheduler Batches can now be exported/imported using a new utility.
System Admin
  • New utility for independently exporting/importing Parameters Sets (of Model Pipelines).
  • Gateway services will now be enabled by default.
  • SAML POST support.
  • Data Studio Options menu is now accessible by mapping DSUSRGRP and no longer necessitate IDENTITY ADMIN and IDENTITY AUTH.
Health and Application Monitoring
  • Standardized logger format across services.
  • Timezone used in logs is now configurable.
  • Improved messaging and removal of redundant logging.
  • Ability to download logs.
Model Catalog
  • Download option now available for models.
  • Support for creating AutoML models.
Datasets
  • Performance improvements: Reduced memory footprint while using in Datasets in Pipelines.
  • Script is now visible to users for seeded transformations.
  • Sample size for profiling is now configurable.
Scheduler Services
  • Ability to execute/schedule a batch with SYSDATE-X days.
  • Support of scheduler notification emails to be configured for particular user.
  • Support of scheduler objects export/import via rest based API's.
  • Support of audit trail for scheduler service objects.
Technology Stack Changes
  • Support for Java 17 and 21
  • Support for OS: OEL9, OEL8 and Solaris
  • Support for Python 3.8-12
  • Additional support for Oracle DB 23 Client (apart from existing 19)
  • The Product now carries updated versions of the following:
    • OJET 18.1
    • Data Studio 25.3.2
    • PGX 25.3.0
    • All third-party libraries upgraded to latest stable versions for improved performance and security.