Key Feature Additions and Changes | ClearScape Analytics ModelOps - Key Feature Additions and Changes - Teradata Vantage

ClearScape Analytics ModelOps User Guide

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Vantage
Release Number
7.0
Published
April 2023
Language
English (United States)
Last Update
2023-04-19
dita:mapPath
rfi1654194187578.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
B700-1175

The following table lists key feature additions and changes in ClearScape Analytics ModelOps releases.

Release (Date) Description
7.0 (April 2023)
  • Updated look and feel consistent with VantageCloud Lake Console, with quality-of-life improvements for Data Scientists, such as improved job log screens, ability to lookup prediction results and others;
  • Added BYOM no-code feature that registers model artifacts, such as PMML, ONNX, and gets automatic model evaluations, deployment and scoring without writing Python code;
  • Added support for SAS BYOM models that allows models trained in SAS and stored in Vantage tables be registered with ModelOps;
  • Introduced internal job scheduler, replaced the use of Apache Airflow.
6.1 (December 2022) Release to all customers.
06.01 (September 2022)
  • Analytics Health Check which provides connection level information on the installed advanced analytics capabilities and the user permissions related to these capabilities.
  • Added Python 3.7 and 3.9 support. 3.9 is now the default option.
  • Improved UX (OneLook UX) by replacing all dialogs with sheets.
  • Minor improvements and bug fixes.
06.0 (June 2022)
  • Model Monitoring (Preview) which provides support for email alerts when feature drift, target drift or quality drift (accuracy, precision, and so on) is detected in production.
  • Feature Catalog (Preview) streamlines feature selection and definition.
  • Intelligent Deployment UX guides users through the options based on the capabilities available in user's system and the model artifacts.
  • Manual trigger (on-demand) of prediction jobs from UI.
  • Email alerting on prediction job failures.
  • View scheduled prediction jobs (executions) and their status along with logs.
  • Minor improvements and bug fixes.