DataRobot Release 6.2 is here! It is packed with innovation for every step of your AI journey, from data to value. The release includes enhanced automated feature discovery (feature engineering), a new comprehensive Autopilot mode for maximum accuracy when you need it, anomaly assessment insights to help you uncover root cause, governed approval workflows in MLOps, and much, much more.
We would very much like to walk you through all of the details of the release in a live environment, but until then, here are some highlights of the release. (And tell us what you think of this release announcement and demos, as well as 6.2 features!)
Next-Level Feature Discovery: An enhanced dataset relationship workflow, makes it much easier to select multiple datasets, and define, edit, and visualize all your relationships at the same time. You can now access logs to get details on which features were explored, discarded, and generated. You can also download the full training dataset, including all the derived features.
Comprehensive Autopilot Mode (PUBLIC BETA): This new mode runs every single model in the repository for your project, taking as long as necessary to maximize accuracy when you need it most. We also have a new Get More Accuracy feature, so you can kick off Autopilot in Quick mode, then start Comprehensive mode only after you’ve seen your initial results.
Anomaly Assessment Insights: New in Automated Time Series 6.2, this interactive visualization allows you to quickly investigate anomalies and anomalous regions in your data, and access SHAP scores for the underlying features causing the anomaly. This allows you to understand the root cause, as well as be able to explore all of your anomalies, panning through different time segments and zooming in to see the detail.
Model Comparison Reimagined: The ability to compare models has taken a huge leap forward in Release 6.2. We worked with our most experienced data scientists to give you the best possible user experience where you can compare models and choose the best for deployment. We have enhanced the Lift Charts, ROC Curve, and Profit Curve, added support for more bins, and have added new tooltips to enhance overall ease of use.
Governed Approval Workflows: Customizable governance policies and review and approval workflows come to MLOps in 6.2. This introduces accountability in your production AI, and enables you to continue to deploy and manage production models while at the same time increasing your overall level of AI governance for your entire organization.
Connect to Remote Repositories: We recognize that your data science teams often govern and manage their models in popular open source code repositories. In Release 6.2, MLOps allows you to connect directly to your GitHub and S3 repositories and dynamically pull model code and model artifacts into DataRobot, making it simple to package, test, deploy, and monitor them in your production environment of choice.
These are just a few of the great new features that we have added based on your feedback. When combined with your ideas, capabilities like these help make your organization truly AI-enabled. For a complete list of all of the new and enhanced features included in DataRobot Release 6.2, please visit the DataRobot Community or our customer support portal.
Public Beta features
Every DataRobot release includes some features that have been tested by our engineering and quality teams, and are available for preview by a limited number of users. If you're a customer and are interested in giving some of these features a try, contact your CFDS or account executive for details on how you can participate.
Here are some public beta features you can check out now:
AI Catalog enhancements for impact analysis
Portable Prediction Servers
Comprehensive modeling mode
Enhanced ability to control stopwords via API
Quantile regression for AutoML
Lemmatizers for English text with WordNet and Spacy
Resources for this release
We’ve created a series of demo videos to help you understand the changes and guide you while using this release. Also, blogs are published periodically so please make sure to check our blog portal often. For the best experience, you can also subscribe to our blog and we’ll notify you when new blogs are posted.
Below are demo videos for many of the new and updated features.
Segmented Analysis (copy and share link to this demo)
Usability Enhancements (copy and share link to this demo)
Portable Prediction Servers (PUBLIC BETA) (copy and share link to this demo)
Custom Model Dependencies (copy and share link to this demo)
Custom Model Testing Enhancements (copy and share link to this demo)
UI/UX Workflow Enhancements
Maintenance Notifications (copy and share link to this demo)
Prediction Thresholds (copy and share link to this demo)
Remove All Jobs (copy and share link to this demo)
Modeling and Evaluation
Comprehensive Autopilot Mode (PUBLIC BETA) (copy and share link to this demo)
Compliance Document Template Builder (copy and share link to this demo)
Model Comparison Reimagined (copy and share link to this demo)
Humble AI Enhancements (copy and share link to this demo)
Download Feature Discovery Values (copy and share link to this demo)
Forecast vs Actuals (copy and share link to this demo)
Anomaly Assessment Insight (copy and share link to this demo)
More information about the release
Make sure to join the release 6.2 webinar which will provide an overview of these new features and product demonstrations.
More information for DataRobot users: search in-app Platform Documentation for Release Center, and find the Version 6.2.0 release notes for AutoML or MLOps.
Tell us what you think
If this material is helpful, let us know. If you still have questions about the release, let us know. Other DataRobot Community members and our DataRobot experts will help fill in any blanks, and your feedback is critical to helping us get better. Click Comment and let us know.
Need a Tip? DataRobot experts are putting together some helpful DataRobot usage tips for the platform, trial, features, etc. You can find these easily in the Tip of the Day board (under Read). Let us know if you've found a good one or have a good one to add!