Training: June 20–21, 2016
Tutorials: June 21, 2016
Keynotes & Sessions: June 22–23, 2016
Santa Clara, CA

Using machine learning to determine drivers of bounce and conversion

Patrick Meenan (Facebook), Tammy Everts (SpeedCurve)
1:15pm–1:55pm Wednesday, 06/22/2016
Performance for the people
Location: Ballroom CD Level: Beginner
Average rating: ****.
(4.38, 16 ratings)

Prerequisite knowledge

Attendees should have general experience with real user measurement and web performance.


There has been a lot of historical work to look at the relationship between performance and conversions, but most of it has been after the fact or relied on linear models. Recently, Google partnered with SOASTA to train a machine-learning model on a large sample of real-world performance, conversion, and bounce data. Patrick Meenan and Tammy Everts offer an overview of the resulting model—able to predict the impact of performance work and other site metrics on conversion and bounce rates and answer questions like:

  • What factors of my site most influence my business metrics?
  • What performance metrics should I focus on?
  • How much faster do I need to make my site to see a measurable impact in conversions?
  • What would the ROI be for improving the site performance?
  • How much is slow performance costing my business?
  • At what point should I expect to see diminishing returns on improving performance?

The code used to generate the model is freely available. Patrick and Tammy demonstrate how to make the most use of it with your own performance data.

Photo of Patrick Meenan

Patrick Meenan


Patrick Meenan is a software engineer at Facebook, where he’s helping make the web faster. Patrick has been working on web performance in one form or another for the last 25 years. Previously, he worked at Cloudflare and Google to make Chrome and the web faster. Patrick created the popular open source WebPageTest web performance measurement tool, runs the free instance of it at, and can frequently be found in the forums helping site owners understand and improve their website performance.

Photo of Tammy Everts

Tammy Everts


Tammy Everts is chief experience officer at SpeedCurve, where she helps companies understand how visitors use their websites, and a cochair of O’Reilly Fluent. Tammy has spent the past two decades studying how people use the web. Since 2009, she’s focused on the intersection between web performance, user experience, and business metrics. Her book, Time Is Money: The Business Value of Web Performance, from O’Reilly, is a distillation of much of this research. She also cocurates (with Tim Kadlec) WPO Stats, a collection of performance case studies.

Comments on this page are now closed.


Picture of Parvez Ahammad
Parvez Ahammad
07/01/2016 7:38pm PDT

Thank you for (hopefully) starting the trend of machine learning talks at Velocity conference. I started writing my feedback from a machine learning practitioner’s point of view, and it quickly became large. I summarized my thoughts here:

Picture of Tammy Everts
06/22/2016 10:29am PDT

Hi Atoosa. I just posted the slides on Slideshare:

Atoosa Rezai
06/22/2016 6:47am PDT

Can you please post your presentation?