~/talk

Machine Learning for Personalization

on YouTube 03m
Talkat O'Reilly Artificial Intelligence Conference 2019 - New York, New York · 2019-04-15..04-18· [machine-learning, data-visualization]

speaker

name:Tony Jebara
links:none on file

resources

video:https://youtu.be/TBukLWxiyXs
slides:none on file

summary

Netflix treats each account as 140 million personalized products, using machine learning to rank catalog items, arrange page layout, pick billboard promotions, and tailor messaging and search. A concrete system selects among multiple box art images for a title (example Stranger Things) and serves the image most predictive of engagement for that profile — teenage cast, horror closeup, or kid-focused shot — and work is underway to fold causality and fairness into those personalization choices.

AI-written summary · about

chapters (4)

  1. 0:00Start
  2. 1:06personalize the imagery
  3. 1:21remove the image aspect from our recommendation engine
  4. 2:00use machine learning to personalize

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.