eHarmony, every mention

7 scenes · ← back to eHarmony

tap a year for its mentions
0010120120132014episodesmentions
01120132014episodes it came up in
00100.520120132014episodesmentions per episode

every year anyone Vaclav Petricek 9Misha Sobolev 6James Gutierrez 2Matt Turck 1

Verbatim, from the transcripts: the passages where eHarmony comes up

loading…

James Gutierrez, Insikt // Data Driven #27 // May 2014 (Hosted by FirstMark Capital) May 29, 2014 · 2 mentions

Vaclav Petricek, eHarmony // Data Driven NYC 19 // October 2013 Dec 5, 2013 · 16 mentions

  • ▶ 0:08 Matt Turck Baklev from eHarmony.
  • ▶ 0:19 Vaclav Petricek Uh, I'm a director of machine learning at eHarmony, uh, based in Santa Monica, and, uh, I would like to tell you how we use machine learning to, uh, to match people.
  • ▶ 3:19 Vaclav Petricek The initial eHarmony model had about 29 dimensions, but over time, as we are collecting more and more data, the models are getting more complex.
  • ▶ 10:17 Vaclav Petricek And so what we are doing is we, um, we have this data on about forty million users who have registered on eHarmony, uh, you know, since the beginning, and we know all these attributes about them, we know thousands of things, uh, and we…
  • ▶ 15:57 Vaclav Petricek Um, so we regularly ask Harris Interactive to go out and, uh, make a survey for us of marriages, and then count how many of them originated on the harmony, etc. 6 times in the scene
  • ▶ 18:36 Misha Sobolev So I understand that eHarmony works on a subscription-based model, so the better you are at the algorithm, the sooner they stop becoming a paying subscriber. 6 times in the scene
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.