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

Aha moments in deep learning at Zendesk

Chris Hausler (Zendesk), Arwen Griffioen (Zendesk)
2:35pm3:15pm Thursday, December 7, 2017
Data science and advanced analytics, Machine Learning
Location: Summit 2 Level: Intermediate
Average rating: ****.
(4.62, 8 ratings)

Who is this presentation for?

  • Data scientists and engineers, software engineers, product managers, and ML people

Prerequisite knowledge

  • Basic knowledge of machine learning

What you'll learn

  • Learn how Zendesk implemented deep learning
  • Explore the evolution of Zendesk's Answer Bot, from tradition machine learning to deep learning

Description

Chris Hausler and Arwen Griffioen discuss Zendesk’s experience with deep learning, using the example of Answer Bot, a question-answering system that resolves support tickets without agent intervention. They cover the benefits Zendesk has already seen and challenges encountered along the way.

Answer Bot uses deep learning to understand customer queries, responding with relevant knowledge base articles that allow customers to self-serve. Research and development behind the ML models underpinning Answer Bot has been rewarding but punctuated with pivotal deviations from the charted course: deep learning was not Zendesk’s first approach. Chris and Arwen walk you through the journey from product ideation to traditional ML approaches with per-customer models to the current release that utilizes word embeddings and recurrent neural networks to provide a single global model that can serve tens of thousands of accounts.

Topics include:

  • Defining the problem space and the metrics Zendesk wanted to optimize for
  • How the team approached the problem with traditional ML
  • Why they chose to take a big bet and pivot to deep learning
  • Getting the team up to speed with deep learning and TensorFlow
  • Why deep learning is great
  • Why deep learning is great—but not magic
  • Processes and frameworks for experimentation, iteration, and validation
Photo of Chris Hausler

Chris Hausler

Zendesk

Chris Hausler leads the data science team at Zendesk, a role he describes as turning lots of data into magic, which he does with the help of machine learning, Python, Hadoop, graphs galore, and amazing colleagues. Over his career, he’s held the titles of data scientist, data engineer, researcher, PhD student, consultant, and programmer.

Photo of Arwen Griffioen

Arwen Griffioen

Zendesk

Arwen Griffioen is a data scientist at Zendesk, where she works on the team producing deep learning solutions for customer self-service. An Oregonian expat who has lived in Melbourne for the past seven years, Arwen is passionate about improving the status of under represented groups in STEM fields and applying machine learning to make the world a little bit better. She holds a PhD in machine learning with a minor in ecoinformatics.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Comments

Kisuk Lee | SOFTWARE ENGINEER
12/22/2017 6:51am +08

Hi I know it might be too late but would you guys share the slides please?
I found the sessions from your company super helpful and wish to share the learnings to my colleagues.
Thank you!