Simply building a successful machine learning product is extremely challenging, and just as much effort is needed to turn that model into a customer-facing product. Drawing on their experience working on Zendesk’s article recommendation product, Wai Yau and Jeffrey Theobald discuss design challenges and real-world problems you may encounter when building a machine learning product at scale.
Wai and Jeffrey cover the evolution of the machine learning system, from individual models per customer (using Hadoop to aggregate the training data) to a universal deep learning model for all customers using TensorFlow, and outline some challenges they faced while building the infrastructure to serve TensorFlow models. They also explore the complexities of seamlessly upgrading to a new version of the model and detail the architecture that handles the constantly changing collection of articles that feed into the recommendation engine.
Wai Chee Yau is a senior data engineer at Zendesk. A polyglot developer who loves working with data and machine learning, she has more than nine years’ experience in data processing, distributed systems, APIs, and system integration across a number of industries. She has completed a PhD in computer vision in 2008.
Jeffrey Theobald is a senior data engineer at Zendesk. Jeffrey has worked in data engineering for eight years, mostly using Python, bash, Ruby, C++, and Java. He has used Hadoop since 2011 and has built analytics and batch processing systems as well as data preparation tools for machine learning.
Comments on this page are now closed.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org