Is your organization ready to deploy analytic models at scale? Are your existing systems connected in the right ways to leverage the latest analytics capabilities? Join us for a live webinar detailing the creation and deployment of gradient boosting machine models using Python, Kafka and FastScore. This webinar, led by Open Data’s Matthew Mahowald, will increase your understanding of the benefits of gradient boosting as well as the easiest way to deploy and maintain a live streaming gradient boosting machine model in production systems.
Our webinar will focus on providing 3 key takeaways:
Learn how to create a gradient boosting machine using SciKit Learn and Python
Understand the steps required to transform features, train, and deploy a GBM using FastScore, a language agnostic analytic engine
See a live demo of a GBM analyzing auto insurance risk
Feb 16, 2017 - 10am PST (1pm EST)
Matthew is a data scientist and software engineer at Open Data Group. He holds a PhD in Mathematics from Northwestern University, where he researched the geometry of string theory and topological field theory. At ODG, Matthew focuses on developing and deploying machine learning models with FastScore.