Presented By O'Reilly and Cloudera
Make Data Work
Dec 4–5, 2017: Training
Dec 5–7, 2017: Tutorials & Conference

The trials of machine learning at Zendesk

Wai Chee Yau (Zendesk), Jeffrey Theobald (Zendesk)
2:35pm3:15pm Wednesday, December 6, 2017
Average rating: ****.
(4.75, 8 ratings)

Who is this presentation for?

  • Data and machine learning engineers

Prerequisite knowledge

  • A basic understanding of data systems and machine learning

What you'll learn

  • Explore Zendesk's article recommendation product and some of the challenges faced while implementing it


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.

Topics include:

  • Infrastructure for continuously changing textual data
  • Deploying and serving TensorFlow models in production
  • Real-world production problems when dealing with a machine learning model
  • Data, customer feedback, and user experience
Photo of Wai Chee Yau

Wai Chee Yau


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.

Photo of Jeffrey Theobald

Jeffrey Theobald


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.


Picture of Jeffrey Theobald
12/15/2017 4:58pm +08

Hey Kisuk,
You can find a PDF copy of the slides that we used on this link,

hopefully they’re useful to you!

12/12/2017 2:29pm +08

Hi This is Kisuk Lee who attended and sincerely enjoyed the sessions from your company.
The experience from your company will help us to make better decision while applying ML and DL on our work.
I wonder if your folks can share the slides that you guys used for your presentation.
It’ll surely help me to share the learnings to my colleagues.
Hope to be replied. Thank you :)