Skip to content
Search at Etsy episode artwork

Oct 7, 2019 1 hr 18 min

Search at Etsy

from Programming Throwdown Hosted by Patrick Wheeler and Jason Gauci

What actually happens when you type something in the search bar at the top of etsy.com and hit enter? This awesome interview with Liangjie Hong, Director of Data Science and Machine Learning, answers that question all the way from the philosophical (what should we show first?) to the inner workings (what is a reverse index and how does it work?).

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Search at Etsy

0:00 1:18:42

Chapters

  1. 0:14 Introduction to Liangjie Hong
  2. 14:14 How Inverted Indices Work
  3. 16:42 Using Embeddings for Semantic Similarity
  4. 18:43 Balancing Short-term and Long-term Goals
  5. 21:14 Measuring Long-Term Customer Value
  6. 23:16 Technical Architecture of Search Results
  7. 25:21 Diverse Technologies in Production
  8. 28:13 The Gap in ML Education
  9. 30:55 Real-World Impact of ML
  10. 33:39 Building Models with Data
  11. 35:22 Machine Learning for Ranking
  12. 42:23 Understanding User Intent
  13. 44:02 Scaling with Small Teams
  14. 46:50 The Role of Cloud Infrastructure
  15. 50:07 The Role of Discovery and Recommendation
  16. 53:15 Balancing New Sellers vs. Established Winners
  17. 56:08 Etsy's Promoted Listings Program
  18. 1:03:05 Roles of Data Scientists vs. Machine Learning Engineers
  19. 1:10:14 The Etsy Interview Process
  20. 1:12:34 Preparing for Technical Interviews
  21. 1:14:52 Etsy Search Overview

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Programming Throwdown?

This episode is 1 hour and 18 minutes long.

When was this Programming Throwdown episode published?

This episode was published on October 7, 2019.

Can I download this Programming Throwdown episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.