Streaming Analytics Framework

[#1]

Deploying real-time analytics projects at scale requires two main components:

• having an approach so simple that a subject matter expert can configure and deploy projects, and
• extensive automation that transforms simple configuration files into complex deployment-ready projects, complete with state-of-the-art machine learning models.

With these principles in mind, the Streaming Analytics Framework was developed as an overlay to VIYA and Event Stream Processing. Users create a visual map of their devices and sensors and then configure real-time updating analytic base tables in a few simple steps. Machine learning models are automatically trained and managed based on the specification of just the target and predictor variable list. Streaming Analytics Framework then automatically builds the Event Stream Processing project which can be deployed in minutes.

The approach has been used successfully for projects focused on energy monitoring, prediction of device failure, optimization of manufacturing plant settings, and is also being positioned for analysis of electronic health records and disaster aversion.

This video introduces the framework and walks you through a real-world example to help you understand the approach. If you are interested in accelerating the deployment of real-time analytics projects for your organization, please see the attached services brief and reach out to our today!