New DataRobot Release Extends Enterprise Readiness Capabilities and Automates Machine Learning in Insurance Industry Pricing Models

Print Friendly, PDF & Email

DataRobot, a leader in machine learning automation, unveiled significant new features in the DataRobot machine learning automation platform, including new model deployment options, SAS integration, and features that make it easier than ever for analysts of any skill level to quickly build and deploy accurate predictive models. DataRobot also unveiled new features specifically for the insurance market, designed to solve some of the toughest use cases in the industry.

This is another significant step forward for the company,” said Jeremy Achin, CEO of DataRobot. “We’re the only software in the market that not only automates the heavy lifting inherent in machine learning, but is built specifically for enterprise deployment. Our next few releases are going to shake the worlds of business, data science and beyond.”

Bringing Enterprise-Ready Data Science to Business Users of All Skill Levels

The new release includes several new features to empower analysts of all skill levels to perform as data scientists, including:

  • Integration with SAS: As the legacy analytics tool of choice for many companies, SAS is deeply embedded in many workflows. DataRobot now ingests SAS files directly, lowering the barriers to working alongside SAS or replacing it altogether. This will smooth the transition for many organizations as they look to move beyond manual, time-consuming modeling approaches, and will de-risk their adoption of open source technologies.
  • Machine Learning-Powered Predictive Modeling for Insurance Pricing: DataRobot’s machine learning automation empowers insurance users to solve predictive modeling problems across marketing, distribution, underwriting, claims management and audit. DataRobot is introducing Generalized Additive Models – a hybrid between easily interpretable Generalized Linear Models and highly accurate machine learning algorithms – to efficiently tackle pricing use cases. These newer sets of algorithms will allow users to solve pricing and risk segmentation problems more accurately, without sacrificing transparency or interpretability. DataRobot will also automatically generate rating tables that product managers and actuaries can directly submit to the Department of Insurance (DoI).
  • Scoring Code Generation:  DataRobot now offers the ability to export data preparation, preprocessing, and scoring code in Java – extending the deployment options beyond low-latency API and distributed scoring via Spark. Scoring code enables ultimate transparency and provides the flexibility to deploy DataRobot models in virtually any environment.

Today, DataRobot solves predictive modeling problems across all core functions in an insurance company. That by itself is a remarkable achievement,” said Satadru Sengupta, General Manager of Insurance at DataRobot. “But what is really differentiating is the user-centric design of the product. DataRobot is a technology company founded and built by people from the insurance industry. We know that successful adoption of machine learning means engaging the users, regulators and consumers.”

DataRobot has been making noise in recent months in the machine learning space. In May, it acquired Nutonian, a data science software company specializing in time series analytical modeling. The new platform enhancements include architectural changes that will enable Nutonian’s product features to be embedded into the DataRobot platform later this year.


Sign up for the free insideBIGDATA newsletter.

Speak Your Mind