Introducing Palladium, an Open Source Platform for Predictive Analytics Services

By CIOReview | Wednesday, April 1, 2015

FREMONT, CA: In order to enable businesses with informed decision making, the Business Intelligence Unit of the Otto Group (called Otto Group BI) has released an open source framework called Palladium which aids in setting up predictive analytics services faster. The company Otto Group is a globally operating retail and services group.

The company has made Palladium as open source and now available on GitHub under the Apache 2.0 license. This project aims to achieve rapid scaling of predictive analytics services and efficient resource utilization. With this platform, organizations can cut down the costs incurred in development and deployment of new predictive analytics services as well as it enables them to fine-tune the core machine learning models to support reliability and scalability of these predictive models.

Works with Docker
Palladium supports tasks such as fitting, evaluating, storing, distributing, and updating models. The product comes with a script that automates creation of Docker images for Palladium services.

Works with Mesosphere
The Mesos and Mesosphere complements Palladium on the datacenter layer; Mesos enables smooth building and running of distributed systems across entire data center and cloud environments for Hadoop deployments and more.

Marathon is a cluster-wide init and control system for services in cgroups or Docker containers. Palladium combined with Marathon and Mesos becomes a highly-scalable and flexible platform for adding predictive intelligence to any business.