Evan Estola - On recommendation systems going bad, hiring ML engineers, giving constructive feedback, filter bubbles and much more - #9
Evan Estola is Director of Engineering at Flatiron Health where he’s leading software engineering teams focused on machine learning products. Prior to this, he was a lead machine learning engineer working at Meetup helping Meetup’s members find the best Meetups near them. Before Meetup, Evan worked on hotel recommendations at Orbitz Worldwide, and he began his career in the Information Retrieval Lab at the Illinois Institute of Technology.
Evan has spent the majority of his career developing recommendation systems and machine learning products. And naturally, it’s the main theme of this episode, and we talk about how recommendation systems go bad. Throughout the episode, Evan shares various stories when recommendation systems didn’t work as expected, like this one time when members saw mathematically worst recommendations for meetups near them. He also shares why Schenectady, NY pops up on some lists of most popular cities and we also discuss the Wall Street Journal article titled “Orbitz steers Mac users to pricier hotels”. Apart from recommendation systems, we discussed the skills Evan looks for when hiring ML engineers, how to give constructive feedback, filter bubbles and much more.
You can read the episode transcript here.
- Evan on Twitter
- Evan on LinkedIn
- WSJ’s post about Orbitz
- Evan’s talk - When recmmendation systems go bad
Music CreditsVlad Gluschenko — Forest
License: Creative Commons Attribution 3.0