Presented By
O’Reilly + Intel AI
Put AI to Work
April 15-18, 2019
New York, NY
Discover opportunities for applied AI
Organizations that successfully apply AI innovate and compete more effectively. How is AI transforming your business?
Be a part of the program—apply to speak by October 16.

ML at Twitter: Deep dive into Twitter's Timeline

1:00pm1:40pm Wednesday, April 17, 2019
Case Studies, Machine Learning
Location: Sutton South
Secondary topics:  AI case studies, Media, Marketing, Advertising, Platforms and infrastructure, Text, Language, and Speech

Who is this presentation for?

Machine Learning Engineers/Software Engineers/Machine Learning Researchers



Prerequisite knowledge

- Tensorflow knowledge - ML basics (architectures, hyperparameter tuning)

What you'll learn

- How to implement ML at a production scale - ML pipeline at Twitter - Optimizations for Sparse Workloads inside of Tensorflow


Machine Learning has allowed Twitter to drive engagement, promote healthier conversations, and deliver catered advertisements.This session will focus on explaining, in depth, the use case of one of teams that benefits from our Machine Learning platform: Timelines Ranking. We plan to discuss its feature pipeline, modeling decisions as well as platform improvements. In the modeling side, we will be discussing hyperparameter tuning as well as different architecture explorations (alongside discretization and isotonic calibration). In the platform side, we will be exploring some of the challenges Twitter faced by working with heavily text-based (sparse) data and some of the improvements we have made in our Tensorflow-based platform to deal with these use cases. Overall, we plan to give a holistic view into one of Twitter’s most prominent use cases.

Photo of Cibele Montez Halasz

Cibele Montez Halasz


Cibele is a Machine Learning Engineer at Twitter Cortex, where she helps to build Twitter’s deep learning platform. Prior to working at Twitter, Cibele worked at Apple as a Data Scientist and Systems Design Engineer; and at Analog Devices as Product Applications Engineer . At Analog Devices, she worked on building machine learning algorithms that use smartphone sensors to understand a person’s behavior. Cibele obtained her B.S. from Stanford University in Electrical Engineering and Physics and her M.S. from the California Institute of Technology in Electrical Engineering with an emphasis in Computer Vision and Machine Learning.

Photo of Mishael Rosenthal

Mishael Rosenthal


Mishael is a Software Engineer at Twitter Timelines Quality team, focusing on relevance-based timelines ranking. Since 2011 Mishael has been utilizing Machine Learning to tackle real-world problems in various domains, such as hardware verification and chat agent allocation. He also has vast experience developing data science tools, pipelines and infrastructure. Mishael obtained his BSc in Mathematics and Computer Science and MSc in Theoretical Computer Science from the Hebrew University of Jerusalem.

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)