Showing results for 
Search instead for 
Did you mean: 

What's New in DataRobot Release 6.0?

Community Team
Community Team
13 0 3,673



DataRobot Release 6.0 takes enterprise AI to the next level, with many ground-breaking new features and capabilities. These include significant improvements to our deep learning capabilities with new Keras-based blueprints for your tabular and text data, new models optimized for images, and LSTM/RNN models for time series use cases.

Here’s a highlight of some of the key features and changes delivered in Release 6.0. (Make sure to tell us what you think of this material.)

Visual AI. Visual AI gives you the ability to easily incorporate image data into your machine learning models alongside traditional text-based data types. It enables your organization to get value from computer vision right away—all with the same DataRobot usability, workflow, visuals, and other UI features you know and love. And, Visual AI opens up powerful new use cases for AI requiring image recognition and classification.

Automated Deep Learning. We recently secured a provisional patent for a new Keras-based model framework that allows you to quickly build and easily understand deep learning models, and then immediately deploy them into production— all with the infrastructure you already have in place (e.g., GPU-accelerated hardware is not needed).

AI Applications. Many organizations struggle with getting the transformational power of AI into the hands of key decision-makers. Now any machine learning model, including DataRobot models and models written in R or Python, can be turned into an AI application, enabling anyone in your organization to interact with the predictive insights of the underlying model. Users get the power to experiment with different scenarios, predict results, and make more informed business decisions.

MLOps. DataRobot MLOps gives you the ability to deploy, monitor, manage, and govern machine learning models in production environments. MLOps now includes pre-packaged model environments so you can drag-and-drop model files (developed in languages such as Python and R) and deploy them to Kubernetes. The release also includes unlimited batch scoring with integration to leading cloud storage providers for massive scale, as well as MLOps monitoring agents that can capture metrics from models deployed to almost any environment.

Automated Time Series Enhancements. Automated Time Series now features new deep learning techniques that remove the traditional forecasting barriers to make easy work of large-scale multi-series applications. Automated support for intra-month seasonality and zero-inflated strategies allow you to create highly accurate forecasts.

DataRobot Paxata Integration. Following the acquisition of Paxata in December 2019, DataRobot has integrated Paxata's AI-assisted data preparation solution seamlessly within the DataRobot AI Catalog to empower novice and expert users to rapidly explore, clean, combine, and shape data for training and deploying machine learning models.

Many Other New Features and Enhancements. Release 6.0 is full of powerful new capabilities you’ll want to take advantage of immediately, including AI Catalog (now enabled by default), multiclass ACE scoring and lift charts, and dozens of usability improvements.

Early release 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 early release features you can check out now:

  • Feature discovery (enhancements)
  • Local deployment of custom models in MLOps
  • Record level storage and extended drift tracking in MLOps
  • Role-Based Access Control (RBAC)
  • Enhanced notifications via webhooks
  • Neural network visualizer
  • Profit curve and payoff matrices
  • Gaussian processes
  • Tableau and Snowflake data source write-back

Resources for this release

We’ve created a series of blogs and demo videos to help you understand the changes and guide you while using this release. New blogs will be published periodically during the next two weeks so please make sure to check our blog portal often. For maximum efficiency 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 features and changes.

Data Access/Preparation & Feature Engineering

AI Catalog Data Connection Creation Flow

Bi-Directional Connectivity to AI Catalog

Integrated Predict Tool

Windowing Functions & Fill Tools

Intelligent Matching With Fuzzy Join

Feature Derivation Logs

Machine Learning

Using Visual AI to Classify Plant Diseases
Clustered Multiseries Models


Deploy Model Package
Custom Model Deployment Flow
Model Registry
Deployment for Monitoring Agent

AI Applications

AI Applications Gallery
Optimizer Application
What-If Application
Predictor Application

Usability Improvements

Target Leakage Enhancements
Prediction Warnings

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!

DataRobot Release 7.1
Ready to learn about changes in the latest release? See the What's New in DataRobot Release 7.1? article, and the DataRobot Release 7.1 (on-demand) webinar. If you have questions about the release, you can ask them right here!

DataRobot + Zepl
The acquisition of Zepl and integration of its self-service data science notebook solution provides additional flexibility for data scientists who prefer to code. Jason's blog post provides an end-to-end DataRobot demo that uses Zepl notebooks. You can check out Zepl today.

New to DataRobot? Check out all the resources to help you get going quickly! See the quick index for Knowledge Base Resources and quick index for Learning Sessions to find links to some great learning content.