Presented By O’Reilly and Cloudera
Make Data Work
September 11, 2018: Training & Tutorials
September 12–13, 2018: Keynotes & Sessions
New York, NY

Infrastructure for deploying machine learning to production in large financial institutions: Lessons learned and best practices

Harish Doddi (Datatron), Jerry Xu (Datatron Technologies)
4:20pm–5:00pm Thursday, 09/13/2018
Secondary topics:  Financial Services, Model lifecycle management

Who is this presentation for?

  • CIOs, CTOs, and vice presidents of engineering and data science

What you'll learn

  • Understand data science lifecycles
  • Discover the challenges when taking models into production
  • Learn best practices for machine learning and deep learning


Large financial institutions have many data science teams (e.g., those for fraud, credit risk, and marketing), each often using diverse set of tools to build predictive models. There are many challenges involved in productionizing these predictive AI models. Harish Doddi and Jerry Xu share challenges and lessons learned deploying AI models to production in large financial institutions.

Harish and Jerry begin by outlining the enterprise data science lifecycle and how the production model deployment flow works. They outline the challenges they faced and how they solved them. Along the way, they explain why monitoring models and managing models in the production should be mandatory.

Photo of Harish Doddi

Harish Doddi


Harish Doddi is cofunder and CEO of Datatron. Previously, he held roles at Oracle; Twitter, where he worked on open source technologies, including Apache Cassandra and Apache Hadoop, and built Blobstore, Twitter’s photo storage platform; Snap, where he worked on the backend for Snapchat Stories; and Lyft, where he worked on the surge pricing model. Harish holds a master’s degree in computer science from Stanford, where he focused on systems and databases, and an undergraduate degree in computer science from the International Institute of Information Technology in Hyderabad.

Photo of Jerry Xu

Jerry Xu

Datatron Technologies

Jerry Xu is cofounder and CTO at Datatron Technologies. An innovative software engineer with extensive programming and design experience in storage systems, online services, mobile, distributed systems, virtualization, and OS kernels, Jerry also has a demonstrated ability to direct and motivate a team of software engineers to complete projects meeting specifications and deadlines. Previously, he worked at Zynga, Twitter, Box, and Lyft, where he built the company’s ETA machine learning model. Jerry is the author of open source project LibCrunch. He’s a three-time Microsoft Gold Star Award winner.