Large Scale CTR Prediction – Lessons Learned

PyData happened in San Francisco two weeks ago and I’m happy to say that I was fortunate enough to be one of the speakers at this fine event. It was three exciting days of meeting interesting people and listening to insightful tutorials and presentations. Big shout out to the organizers who put the conference together on a voluntary basis. Videos of all the talks can be found here.

As already mentioned, I had the opportunity to represent Yelp, speaking about:
“Large Scale CTR Prediction – Lessons Learned”.

Here’s the video with a brief description of the covered content below:

“Starting with a basic setup for click-through rate (CTR) prediction, we will step by step improve on it by incorporating the lessons we’ve learned from operating and scaling such a mission-critical system. The presented lessons will be related to infrastructure, model comprehension, and specifics like how to deal with thresholds. They should be applicable to most ML models used in production.”

Let me know what you think of it in the comments below or in case you have any questions. Happy Friday!

Large Scale CTR Prediction – Lessons Learned was posted in Machine Learning by Florian Hartl.

Feedback

Your email address will not be published. Required fields are marked *

*