What Online Dating Taught Me About Algorithms
summary
History of dating services starts with St James and Operation Match using mailed questionnaires, punch cards and outputting six names and phone numbers; compatibility uses weighted ordinal encoding and Euclidean/KNN-style similarity. OKCupid computes a match percentage via weighted scoring and geometric mean, then adjusts for unread messages, attractiveness and a random factor. Tinder relies on an Elo score style ranking (examples show a 200→182 drop after a swipe), and Hinge applies the Gale‑Shapley stable matching approach.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 1:271960s computer dating
- 8:54OKCupid algorithm deep dive
- 17:47Modern dating app matchmaking
- 22:24Hinge and Gale-Shapley
- 27:43Takeaways and conclusions
related talks
26mWhat Online Dating Taught Me about Algorithms
35mDating Algorithms: What Are They Really Optimizing?
47mAlgorithmic bias is everywhere (especially at Breeze) - what can we do about it?
31mHow to Find Your Other Half or Why Algorithms Matter
25mDr. Steve Liu, Chief Scientist, Tinder
37mExtracting Insight From A Muslim Marriage App
06mMachine Learning for Phone-Based Relationship Estimation: The Need to Consider Population ...
21mEvan Estola, Lead Machine Learning Engineer, Meetup, NYC 2017