Automated Machine Learning and Artificial Intelligence (AI) with DataRobot

Human-centric design, ideal for business users

Domain expertise is the key to developing effective predictive models. DataRobot enables business users to generate accurate models quickly and perform sophisticated data science functions directly.

Built-in guardrails

With DataRobot, modeling projects follow a consistent methodology based on best practices so users can’t “forget” to perform a critical step, such as model validation.

Beschleunigt die Modellauswertung

DataRobot erstellt eine Rangliste, auf der Sie sehen können, welche Modelle mit Ihren Daten am besten funktionieren und bietet Ihnen die Werkzeuge, die Sie benötigen, um die einzelnen Datenmodelle zu vergleichen und zu erkunden. 

Speeds model evaluation

DataRobot builds a leaderboard so you can see which models perform best with your data, and provides the tools you need to explore and compare individual models.

Unsupervised anomaly detection

Uncover anomalies in a dataset with DataRobot's unsupervised ensemble blend model, which can offer new insights even in familiar datasets.

Builds the workflow for you

DataRobot creates the predictive modeling workflow for you. It knows what to do at each step of the process, and does it automatically, without prior programming or manual input from users.

Automates feature engineering

DataRobot prepares data automatically, performing operations like one-hot encoding, missing imputation, text mining, and standardization to transform features for optimal results.

Leverages innovative open source engines

To harness the most advanced techniques, DataRobot uses open source machine learning libraries like R, scikit-learn, TensorFlow, Vowpal Wabbit, Spark ML, and XGBoost.

Supports advanced tuning

DataRobot automates model tuning, but also supports manual tuning so data scientists can tune and adjust machine learning algorithms for even better results.

Multiclass model support

DataRobot allows for classification on targets with up to 10 distinct values, offering both real-time and batch support for uncovering the predictive class and showing its probability across all classes.

Use on-premise or in the cloud

On-premise: You can deploy DataRobot onpremise on standalone servers, an existing Hadoop infrastructure, or in a Virtual Private Cloud (VPC).

Cloud: The DataRobot Cloud is hosted on Amazon Web Services (AWS), delivering the flexibility and speed necessary for any enterprise.

Leverages distributed processing

DataRobot leverages modern distributed processing, running experiments in parallel to radically reduce the time it takes to run a complete data science project.

Enables rapid collaboration

With DataRobot, business users, data scientists, and stakeholders work together on machine learning projects to deliver better results with less wasted effort.

Eliminates model deployment bottlenecks

There are multiple options for deploying your finished models with DataRobot, including native scoring, exportable prediction code, and prediction APIs for real-time and batch scoring.

Resource monitoring and reporting

DataRobot’s Resource Monitor feature provides a view of platform usage across the organization, including which workers and models are taking up runtime, enabling effective resource planning.

Integrates with Hadoop

DataRobot uses your Hadoop distribution’s application management services to distribute runtime libraries to Hadoop Data nodes. Working directly with HDFS, running predictions in DataRobot does not require a proprietary storage layer or the movement of data to an edge node. The DataRobot workload runs in YARN containers, so you do not need to partition your cluster to prevent resource conflicts.

Works with enterprise data

No matter where your data resides – relational databases, Hadoop clusters, text files, or other sources – DataRobot quickly and easily connects to your data source.

Explainable models

Users can download DataRobot’s diagnostic charts, data, and documentation to share them with executives, stakeholders, and regulators.

Supports advanced security

DataRobot offers native security for fine-grained role-based authorization and supports Kerberos and LDAP protocols. In Hadoop, it works with your existing encryption policies.

Editable rating tables

Customizable rating tables allow users to edit and manipulate the tables according to their unique business rules, allowing for an optimal blend of machine learning and human experience.