SlideShare ist ein Scribd-Unternehmen logo
1 von 28
Generating a Billion Personal News Feeds
Lessons Learned from News Feed Ranking
Ewa Dominowska
1 News Feed Overview
2 Machine Learning in News Feed
3 Measurement
What is Facebook News Feed?
Way to connect with stories that matter to you most
Connect, Inform and Entertain
News Feed is the constantly updating list of stories in the middle of your home
page or mobile app. News Feed includes status updates, photos, videos,
links, app activity and likes from people, pages and groups that you follow
on Facebook.
Feed Ranking is just a tool, you are in control of what you see in your News
Feed and can adjust your settings.
▪ Over 1,000,000,000 daily users
▪ Hundreds of billions stories seen
per day
▪ Trillions of stories ranked per day
▪ Publish -> In Feed < 1s
▪ Retrieval + rank time < 200ms
Basic Stats
Alex Chapel
Francis McDonough
Victoria Beckchen
Deliver everything that matters to people
and nothing that doesn't
▪ Don’t miss any important stories
▪ New stories should show up within seconds
▪ Put the best content at the top
▪ People notice/interact with
content at the top first.
▪ Better content at top means
better experience, less good
content missed.
▪ It’s not just winner takes all
ordering of content matters
How News Feed Works?
Story 1
PHOTO
Story 2
FRIEND
POST
Story 3
VIDEO
Story 4
LINK
SHARE
Story 5
PHOTO
Story 6
LINK
SHARE
Story 7
FRIEND
POST
▪ Goal is to put best content on top
▪ Solution – every time you visit we
rank all new content and put on top
▪ Anything you haven’t seen
is new to you
▪ New friend shares same link you’ve seen
▪ Unseen old stories
▪ Seen stories with new
comments
▪ For frequent users ranking
is almost chronological
▪ Diversity of content matters
9:00 AM
1.9
1.1
0.8
0.6
0.4
0.3
0.4
Story 4
LINK
SHARE
Story 5
PHOTO
Story 6
LINK
SHARE
Story 7
FRIEND
POST
0.9
0.6
0.3
0.2
Story 8
PAGE POST
Story 3
F_comment 1.0
1.3
10:00 AM
Story 5
PHOTO
0.1
0.9
Story 9
VIDEO
10:10 AM
Story 10
FRIEND
POST
1.8
Story 11
LINK
SHARE
1.5
Story 12
FRIEND
POST
1.1
Story 13
VIDEO 0.2
12:00 PM
Machine Learning in News Feed
Scoring based Ranking
▪ Given a potential feed story, how
good is it?
▪ Express as probability of click, like,
comment, etc.
▪ Assign different weights to different
events, according to significance
▪ Example: close coworker feels
earthquake
▪ Highest chance of click
▪ Decent chance of like/comment
Event Probability Value*
Click 5.1% 1
Like 2.9% 5
Comment 0.55% 20
Share 0.00005% 40
Friend 0.00003% 50
Hide 0.00002% -100
Total 0.306
*Example, not real values
▪ Why this structure:
▪ Uses Machine Learning to predict true, measurable behavior
▪ Models train on their own data
▪ Allows fast iteration
▪ Allows distributed development
▪ Allows for easy ranking of heterogeneous content
▪ Allows for value to be adjusted independently
▪ WORKS WELL IN PRACTICE
Learnings
Role of Network Structure
▪ News Feed delivers content from
friends along social network
▪ Understanding the network is
key to defining quality
▪ Who are your close friends?
▪ Whose photos do you always like?
▪ Whose links are the most interesting
to you?
Click Like Comment Weighted
Sum
Joe 0.012 0.0042 0.00082 0.0494
Susan 0.023 0.02 0.0082 0.287
Li 0.012 0.0037 0.001 0.0505
0.287
0.0494 0.0505
Joe
Susan
Li
Feature Selection (BDTs)
▪ Start with over >100K potential (dense) features and all historical activity
▪ First, prune these to top ~2K
▪ Training time is proportional to number of examples * number of features
▪ Under-sample negative examples (impressions, no action) to help with # of examples
▪ Start with 100K features, max rows, keep most important 10K, train 10x rows
▪ Do this for each feed event type: train many forests
▪ Historical counts and propensity are some of the strongest features
Model Training (Logistic regression)
▪ We need to react quickly and incorporate new content - use a simple model
▪ Logistic regression is simple, fast and easy to distribute
▪ Treat the trees as feature transforms, each one turning the input features into
a set of categorical features, one per tree.
▪ Use logistic regression for online learning to quickly re-learn leaf weights
F3
-0.1 0.3
0.2
F1
-0.5
0.2 -.05
F2
F3
Throw out boosted tree weights, use only transforms
Input: (F1, F2, F3)
Output (T1, T2) where T1  {Leaves of tree 1}
Stacking: Combined Tree + LR Model
▪ Main Advantage: Tree application is computationally expensive and slow
▪ Reuse click tree to predict likes, comments, etc.
▪ Only slightly more expensive than independent models; better prediction
performance – transfer learnings
~Thousands of
Raw features
Thousands of Tree Transforms
Sparse Boolean features + non-tree raw features
Like Comment Share Friend Outbound
Click
Follow HideClick
Click Like Comment Share Friend Outbound click Follow Hide
Other models + sparse features
▪ Train Neural nets to predict events
▪ Discard final layer, use final layer outputs as features
▪ Add sparse features such as text or content ID
Raw
Features
Forest
Raw
Features
Neural Network
Sparse features
Logistic Regression
Like Comment Share Hide Outbound
Click
Fan | Follow FriendClick
▪ Data freshness matters – simple models allows for online learning and
twitch response
▪ Feature generation is part of the modeling process
▪ Stacking
▪ supports plugging-in new algorithms and features easily
▪ works very well in practice
▪ Use skewed sampling to manage high data volumes
▪ Historical counters as features provides highly predictive features, easy
to update online
Learnings
Measurement
Measurement
18
▪ Selecting the right objective function
▪ Defining metrics
▪ Implicit: Engagement, ex. Click
▪ Longitudinal metrics, ex. Abandonment
▪ Explicit: Quality, ex. Survey Score
Why are implicit metrics limited?
▪ Some important stories don’t
get that much engagement
▪ Eg. Sad stories and world news
▪ Some lower quality stories get lots of
engagement, social expectations
▪ Relative importance: Is comment
always more important then a like?
▪ Goal is to align ranking with
personalized relevance
▪ Solution -> Ask users directly:
Collect explicit signals from survey
data
Pairwise Comparison
Survey
20
▪ Pair wise comparison
between two stories
from same feed.
▪ Pro: Real user preference
on two stories from same
query.
▪ Con: Don’t really know if
they are just comparing
two good stories, or two
poor stories or one of
each.
In or Out survey
21
▪ Single Story survey, “do
you want to see it or
not?”
▪ Pro: Fun, simple, absolute
▪ Con: People do not really
know the consequence of
the action, limited
resolution does not help
with ranking
Rating Survey
22
▪ 5pt rating scale, “how
much do you want to
see the story in your
feed?”.
▪ Pro: Absolute metrics,
good participant rate.
▪ Con: Out of context, raters
might not be truthful,
harder to do for users.
In-Context Survey
23
▪ 5pt rating scale, “how
much do you want to
see the story in your
feed?”.
▪ Pro: In context
▪ Con: Can distract, lead to
abandonment, takes up
valuable real-estate from
the feed
Absolute vs. relative ratings
▪ Relative
▪ Easier
▪ Infinite precision
▪ More self-consistent
▪ More calibrated cross people
▪ Absolute
▪ Gives amount of delta
▪ No intransitivity issues
▪ Clear definition of best
▪ Which one do we choose?
▪ Solution: Do both
Start to better understand what matters for each
individual
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
Definitely do
NOT want to
see this in Feed
Do not want to
see in Feed
Don't mind
seeing in Feed
but wouldn't
mind missing
either
Want to see in
Feed
Definitely want
to see in feed
Someone you really don't care about Someone you don't care about
Someone you somewhat care about Someone you care about
Someone you really care about
Improving Feed based on rating results
▪ Not enough data to do large
scale, personalized machine
learning
▪ Look for other insights
▪ Eg. How much should we value a
comment vs. a like
▪ Ranking by
α p(like) + β p(comment)
▪ Optimal α, β depends on content
type, content creator, context
▪ Passive consumption (dwell time)
prediction improves relevance
▪ Response means different things in
different contexts and for different
people
▪ Eg: ‘like’ is harder to come by on public
content than friend content, and hence tends
to indicate higher quality there.
P(like)P(outboundclick)
Rating vs. p(like) and p(outbound click)
Avg.Rating
Learnings
▪ Both implicit and explicit signals are important and can be used
together
▪ Multiple survey types can be used simultaneously to get different
advantages
▪ Metrics are important - the right metrics are needed to define an
objective function for our models and to measure model performance
▪ ML and Metrics are tools that let us CONNECT, INFORM and
ENTERTAIN Facebook users.
We far from done…
Come join us to help solve the next big
challenge

Weitere ähnliche Inhalte

Was ist angesagt?

kaggle hm fashion recsys pjct 발표 자료.pptx
kaggle hm fashion recsys pjct 발표 자료.pptxkaggle hm fashion recsys pjct 발표 자료.pptx
kaggle hm fashion recsys pjct 발표 자료.pptxJohnKim663844
 
ML Infra for Netflix Recommendations - AI NEXTCon talk
ML Infra for Netflix Recommendations - AI NEXTCon talkML Infra for Netflix Recommendations - AI NEXTCon talk
ML Infra for Netflix Recommendations - AI NEXTCon talkFaisal Siddiqi
 
Tableau Conference 2018: Binging on Data - Enabling Analytics at Netflix
Tableau Conference 2018: Binging on Data - Enabling Analytics at NetflixTableau Conference 2018: Binging on Data - Enabling Analytics at Netflix
Tableau Conference 2018: Binging on Data - Enabling Analytics at NetflixBlake Irvine
 
웹수집(Web Crawling)
웹수집(Web Crawling)웹수집(Web Crawling)
웹수집(Web Crawling)wang inyoung
 
Learning to Rank Presentation (v2) at LexisNexis Search Guild
Learning to Rank Presentation (v2) at LexisNexis Search GuildLearning to Rank Presentation (v2) at LexisNexis Search Guild
Learning to Rank Presentation (v2) at LexisNexis Search GuildSujit Pal
 
Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...
Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...
Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...Flink Forward
 
Context Aware Recommendations at Netflix
Context Aware Recommendations at NetflixContext Aware Recommendations at Netflix
Context Aware Recommendations at NetflixLinas Baltrunas
 
Homepage Personalization at Spotify
Homepage Personalization at SpotifyHomepage Personalization at Spotify
Homepage Personalization at SpotifyOguz Semerci
 
왕초보, 코딩없이 챗봇 만들기
왕초보, 코딩없이 챗봇 만들기왕초보, 코딩없이 챗봇 만들기
왕초보, 코딩없이 챗봇 만들기deepseaswjh
 
Artwork Personalization at Netflix
Artwork Personalization at NetflixArtwork Personalization at Netflix
Artwork Personalization at NetflixJustin Basilico
 
Music Personalization At Spotify
Music Personalization At SpotifyMusic Personalization At Spotify
Music Personalization At SpotifyVidhya Murali
 
Shallow and Deep Latent Models for Recommender System
Shallow and Deep Latent Models for Recommender SystemShallow and Deep Latent Models for Recommender System
Shallow and Deep Latent Models for Recommender SystemAnoop Deoras
 
In the Know 2: Whats New in Social Media?
In the Know 2: Whats New in Social Media? In the Know 2: Whats New in Social Media?
In the Know 2: Whats New in Social Media? CDC NPIN
 
Qcon SF 2013 - Machine Learning & Recommender Systems @ Netflix Scale
Qcon SF 2013 - Machine Learning & Recommender Systems @ Netflix ScaleQcon SF 2013 - Machine Learning & Recommender Systems @ Netflix Scale
Qcon SF 2013 - Machine Learning & Recommender Systems @ Netflix ScaleXavier Amatriain
 
Data council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at NetflixData council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at NetflixGrace T. Huang
 
AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지
AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지
AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지Changje Jeong
 
대용량 로그분석 Bigquery로 간단히 사용하기
대용량 로그분석 Bigquery로 간단히 사용하기대용량 로그분석 Bigquery로 간단히 사용하기
대용량 로그분석 Bigquery로 간단히 사용하기Jaikwang Lee
 
Time, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender SystemsTime, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender SystemsYves Raimond
 
Contextualization at Netflix
Contextualization at NetflixContextualization at Netflix
Contextualization at NetflixLinas Baltrunas
 
In the Know II: Creating Your Social Media Plan
In the Know II: Creating Your Social Media PlanIn the Know II: Creating Your Social Media Plan
In the Know II: Creating Your Social Media PlanCDC NPIN
 

Was ist angesagt? (20)

kaggle hm fashion recsys pjct 발표 자료.pptx
kaggle hm fashion recsys pjct 발표 자료.pptxkaggle hm fashion recsys pjct 발표 자료.pptx
kaggle hm fashion recsys pjct 발표 자료.pptx
 
ML Infra for Netflix Recommendations - AI NEXTCon talk
ML Infra for Netflix Recommendations - AI NEXTCon talkML Infra for Netflix Recommendations - AI NEXTCon talk
ML Infra for Netflix Recommendations - AI NEXTCon talk
 
Tableau Conference 2018: Binging on Data - Enabling Analytics at Netflix
Tableau Conference 2018: Binging on Data - Enabling Analytics at NetflixTableau Conference 2018: Binging on Data - Enabling Analytics at Netflix
Tableau Conference 2018: Binging on Data - Enabling Analytics at Netflix
 
웹수집(Web Crawling)
웹수집(Web Crawling)웹수집(Web Crawling)
웹수집(Web Crawling)
 
Learning to Rank Presentation (v2) at LexisNexis Search Guild
Learning to Rank Presentation (v2) at LexisNexis Search GuildLearning to Rank Presentation (v2) at LexisNexis Search Guild
Learning to Rank Presentation (v2) at LexisNexis Search Guild
 
Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...
Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...
Flink Forward Berlin 2017: Dongwon Kim - Predictive Maintenance with Apache F...
 
Context Aware Recommendations at Netflix
Context Aware Recommendations at NetflixContext Aware Recommendations at Netflix
Context Aware Recommendations at Netflix
 
Homepage Personalization at Spotify
Homepage Personalization at SpotifyHomepage Personalization at Spotify
Homepage Personalization at Spotify
 
왕초보, 코딩없이 챗봇 만들기
왕초보, 코딩없이 챗봇 만들기왕초보, 코딩없이 챗봇 만들기
왕초보, 코딩없이 챗봇 만들기
 
Artwork Personalization at Netflix
Artwork Personalization at NetflixArtwork Personalization at Netflix
Artwork Personalization at Netflix
 
Music Personalization At Spotify
Music Personalization At SpotifyMusic Personalization At Spotify
Music Personalization At Spotify
 
Shallow and Deep Latent Models for Recommender System
Shallow and Deep Latent Models for Recommender SystemShallow and Deep Latent Models for Recommender System
Shallow and Deep Latent Models for Recommender System
 
In the Know 2: Whats New in Social Media?
In the Know 2: Whats New in Social Media? In the Know 2: Whats New in Social Media?
In the Know 2: Whats New in Social Media?
 
Qcon SF 2013 - Machine Learning & Recommender Systems @ Netflix Scale
Qcon SF 2013 - Machine Learning & Recommender Systems @ Netflix ScaleQcon SF 2013 - Machine Learning & Recommender Systems @ Netflix Scale
Qcon SF 2013 - Machine Learning & Recommender Systems @ Netflix Scale
 
Data council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at NetflixData council SF 2020 Building a Personalized Messaging System at Netflix
Data council SF 2020 Building a Personalized Messaging System at Netflix
 
AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지
AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지
AWS를 활용하여 Daily Report 만들기 : 로그 수집부터 자동화된 분석까지
 
대용량 로그분석 Bigquery로 간단히 사용하기
대용량 로그분석 Bigquery로 간단히 사용하기대용량 로그분석 Bigquery로 간단히 사용하기
대용량 로그분석 Bigquery로 간단히 사용하기
 
Time, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender SystemsTime, Context and Causality in Recommender Systems
Time, Context and Causality in Recommender Systems
 
Contextualization at Netflix
Contextualization at NetflixContextualization at Netflix
Contextualization at Netflix
 
In the Know II: Creating Your Social Media Plan
In the Know II: Creating Your Social Media PlanIn the Know II: Creating Your Social Media Plan
In the Know II: Creating Your Social Media Plan
 

Andere mochten auch

Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017
Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017 Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017
Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017 MLconf
 
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016MLconf
 
Anjuli Kannan, Software Engineer, Google at MLconf SF 2016
Anjuli Kannan, Software Engineer, Google at MLconf SF 2016Anjuli Kannan, Software Engineer, Google at MLconf SF 2016
Anjuli Kannan, Software Engineer, Google at MLconf SF 2016MLconf
 
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16MLconf
 
Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...
Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...
Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...MLconf
 
Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016
Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016
Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016MLconf
 
Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017
Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017
Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017MLconf
 
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017MLconf
 
Erik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better MortgageErik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better MortgageMLconf
 
Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016
Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016
Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016MLconf
 
Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16
Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16
Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16MLconf
 
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017MLconf
 
Yuri M. Brovman, Data Scientist, eBay
Yuri M. Brovman, Data Scientist, eBayYuri M. Brovman, Data Scientist, eBay
Yuri M. Brovman, Data Scientist, eBayMLconf
 
Jeff Bradshaw, Founder, Adaptris
Jeff Bradshaw, Founder, AdaptrisJeff Bradshaw, Founder, Adaptris
Jeff Bradshaw, Founder, AdaptrisMLconf
 
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16MLconf
 
Daniel Shank, Data Scientist, Talla at MLconf SF 2016
Daniel Shank, Data Scientist, Talla at MLconf SF 2016Daniel Shank, Data Scientist, Talla at MLconf SF 2016
Daniel Shank, Data Scientist, Talla at MLconf SF 2016MLconf
 
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017MLconf
 
Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016
Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016
Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016MLconf
 
Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016
Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016
Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016MLconf
 
Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016
Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016
Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016MLconf
 

Andere mochten auch (20)

Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017
Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017 Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017
Byron Galbraith, Chief Data Scientist, Talla, at MLconf NYC 2017
 
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
Nikhil Garg, Engineering Manager, Quora at MLconf SF 2016
 
Anjuli Kannan, Software Engineer, Google at MLconf SF 2016
Anjuli Kannan, Software Engineer, Google at MLconf SF 2016Anjuli Kannan, Software Engineer, Google at MLconf SF 2016
Anjuli Kannan, Software Engineer, Google at MLconf SF 2016
 
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
 
Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...
Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...
Jean-François Puget, Distinguished Engineer, Machine Learning and Optimizatio...
 
Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016
Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016
Brian Lucena, Senior Data Scientist, Metis at MLconf SF 2016
 
Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017
Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017
Mayur Thakur, Managing Director, Goldman Sachs, at MLconf NYC 2017
 
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
 
Erik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better MortgageErik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better Mortgage
 
Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016
Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016
Harm van Seijen, Research Scientist, Maluuba at MLconf SF 2016
 
Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16
Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16
Ted Willke, Sr Principal Engineer, Intel at MLconf SEA - 5/20/16
 
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
Irina Rish, Researcher, IBM Watson, at MLconf NYC 2017
 
Yuri M. Brovman, Data Scientist, eBay
Yuri M. Brovman, Data Scientist, eBayYuri M. Brovman, Data Scientist, eBay
Yuri M. Brovman, Data Scientist, eBay
 
Jeff Bradshaw, Founder, Adaptris
Jeff Bradshaw, Founder, AdaptrisJeff Bradshaw, Founder, Adaptris
Jeff Bradshaw, Founder, Adaptris
 
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
 
Daniel Shank, Data Scientist, Talla at MLconf SF 2016
Daniel Shank, Data Scientist, Talla at MLconf SF 2016Daniel Shank, Data Scientist, Talla at MLconf SF 2016
Daniel Shank, Data Scientist, Talla at MLconf SF 2016
 
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
 
Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016
Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016
Alex Smola, Director of Machine Learning, AWS/Amazon, at MLconf SF 2016
 
Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016
Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016
Elena Grewal, Data Science Manager, Airbnb at MLconf SF 2016
 
Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016
Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016
Rajat Monga, Engineering Director, TensorFlow, Google at MLconf 2016
 

Ähnlich wie Ewa Dominowska, Engineering Manager, Facebook at MLconf SEA - 5/20/16

Becoming a Salesforce / Data Driven Non-Profit
Becoming a Salesforce / Data Driven Non-ProfitBecoming a Salesforce / Data Driven Non-Profit
Becoming a Salesforce / Data Driven Non-ProfitSarah Parise
 
Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...
Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...
Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...EnDigiCom
 
Herding Tigers: Helping Writers Let Go of Inline Links
Herding Tigers: Helping Writers Let Go of Inline LinksHerding Tigers: Helping Writers Let Go of Inline Links
Herding Tigers: Helping Writers Let Go of Inline LinksMysti Berry
 
How to Use Data for Product Success with Jet.com Data Manager
How to Use Data for Product Success with Jet.com Data ManagerHow to Use Data for Product Success with Jet.com Data Manager
How to Use Data for Product Success with Jet.com Data ManagerProduct School
 
The Content Selfie: What to Serve Your Customers to Make Them Want You
The Content Selfie: What to Serve Your Customers to Make Them Want YouThe Content Selfie: What to Serve Your Customers to Make Them Want You
The Content Selfie: What to Serve Your Customers to Make Them Want YouSocial Media Today
 
Leveraging Facebook Marketing, Insights and EdgeRank for Small Business
Leveraging Facebook Marketing, Insights and EdgeRank for Small BusinessLeveraging Facebook Marketing, Insights and EdgeRank for Small Business
Leveraging Facebook Marketing, Insights and EdgeRank for Small BusinessJoshua Panzer
 
UX Field Research Toolkit - A Workshop at Big Design - 2017
UX Field Research Toolkit - A Workshop at Big Design - 2017UX Field Research Toolkit - A Workshop at Big Design - 2017
UX Field Research Toolkit - A Workshop at Big Design - 2017Kelly Moran
 
DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...
DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...
DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...Morning Dough
 
Salesforce Social studio February 2016 Release Notes
Salesforce Social studio February 2016 Release NotesSalesforce Social studio February 2016 Release Notes
Salesforce Social studio February 2016 Release NotesRobin Leonard
 
Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011
Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011
Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011Aaron Kronis
 
The Content Selfie - What To Serve Your Customers To Make Them Want You?
The Content Selfie - What To Serve Your Customers To Make Them Want You?The Content Selfie - What To Serve Your Customers To Make Them Want You?
The Content Selfie - What To Serve Your Customers To Make Them Want You?Tangerine Lab
 
How to perform a user test?
How to perform a user test?How to perform a user test?
How to perform a user test?Edumarketeer
 
This is Why No One Reads Your Newsletter - Updated March 2014
This is Why No One Reads Your Newsletter - Updated March 2014This is Why No One Reads Your Newsletter - Updated March 2014
This is Why No One Reads Your Newsletter - Updated March 2014Here's My Chance
 
How to Get Better email Engagement in 2015
How to Get Better email Engagement in 2015How to Get Better email Engagement in 2015
How to Get Better email Engagement in 2015WhatCounts, Inc.
 
Customer Lifecycle Messaging (Matthew Butlein)
Customer Lifecycle Messaging (Matthew Butlein)Customer Lifecycle Messaging (Matthew Butlein)
Customer Lifecycle Messaging (Matthew Butlein)Monetate
 
The Hive Think Tank: Machine Learning at Pinterest by Jure Leskovec
The Hive Think Tank: Machine Learning at Pinterest by Jure LeskovecThe Hive Think Tank: Machine Learning at Pinterest by Jure Leskovec
The Hive Think Tank: Machine Learning at Pinterest by Jure LeskovecThe Hive
 
Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...
Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...
Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...LinkedIn
 

Ähnlich wie Ewa Dominowska, Engineering Manager, Facebook at MLconf SEA - 5/20/16 (20)

Becoming a Salesforce / Data Driven Non-Profit
Becoming a Salesforce / Data Driven Non-ProfitBecoming a Salesforce / Data Driven Non-Profit
Becoming a Salesforce / Data Driven Non-Profit
 
Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...
Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...
Analytics, reporting and ROI, Presentation EnDigiCom LTTA 1 by Jasna Suhadolc...
 
Herding Tigers: Helping Writers Let Go of Inline Links
Herding Tigers: Helping Writers Let Go of Inline LinksHerding Tigers: Helping Writers Let Go of Inline Links
Herding Tigers: Helping Writers Let Go of Inline Links
 
Writing Effective Association Email
Writing Effective Association EmailWriting Effective Association Email
Writing Effective Association Email
 
Project Outcome Webinar
Project Outcome WebinarProject Outcome Webinar
Project Outcome Webinar
 
How to Use Data for Product Success with Jet.com Data Manager
How to Use Data for Product Success with Jet.com Data ManagerHow to Use Data for Product Success with Jet.com Data Manager
How to Use Data for Product Success with Jet.com Data Manager
 
The Content Selfie: What to Serve Your Customers to Make Them Want You
The Content Selfie: What to Serve Your Customers to Make Them Want YouThe Content Selfie: What to Serve Your Customers to Make Them Want You
The Content Selfie: What to Serve Your Customers to Make Them Want You
 
Leveraging Facebook Marketing, Insights and EdgeRank for Small Business
Leveraging Facebook Marketing, Insights and EdgeRank for Small BusinessLeveraging Facebook Marketing, Insights and EdgeRank for Small Business
Leveraging Facebook Marketing, Insights and EdgeRank for Small Business
 
UX Field Research Toolkit - A Workshop at Big Design - 2017
UX Field Research Toolkit - A Workshop at Big Design - 2017UX Field Research Toolkit - A Workshop at Big Design - 2017
UX Field Research Toolkit - A Workshop at Big Design - 2017
 
DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...
DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...
DMIEXPO - Keith Kouzmanoff - The Essential Strategies for Effective Inbox Del...
 
Salesforce Social studio February 2016 Release Notes
Salesforce Social studio February 2016 Release NotesSalesforce Social studio February 2016 Release Notes
Salesforce Social studio February 2016 Release Notes
 
Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011
Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011
Aaron Kronis - Social Media for Retailers - Retail Camp April 9th, 2011
 
The Content Selfie - What To Serve Your Customers To Make Them Want You?
The Content Selfie - What To Serve Your Customers To Make Them Want You?The Content Selfie - What To Serve Your Customers To Make Them Want You?
The Content Selfie - What To Serve Your Customers To Make Them Want You?
 
How to perform a user test?
How to perform a user test?How to perform a user test?
How to perform a user test?
 
This is Why No One Reads Your Newsletter - Updated March 2014
This is Why No One Reads Your Newsletter - Updated March 2014This is Why No One Reads Your Newsletter - Updated March 2014
This is Why No One Reads Your Newsletter - Updated March 2014
 
How to Get Better email Engagement in 2015
How to Get Better email Engagement in 2015How to Get Better email Engagement in 2015
How to Get Better email Engagement in 2015
 
Customer Lifecycle Messaging (Matthew Butlein)
Customer Lifecycle Messaging (Matthew Butlein)Customer Lifecycle Messaging (Matthew Butlein)
Customer Lifecycle Messaging (Matthew Butlein)
 
The Hive Think Tank: Machine Learning at Pinterest by Jure Leskovec
The Hive Think Tank: Machine Learning at Pinterest by Jure LeskovecThe Hive Think Tank: Machine Learning at Pinterest by Jure Leskovec
The Hive Think Tank: Machine Learning at Pinterest by Jure Leskovec
 
Pro bono OR webinar - Making sense of data
Pro bono OR webinar - Making sense of data Pro bono OR webinar - Making sense of data
Pro bono OR webinar - Making sense of data
 
Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...
Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...
Live Customer Webinar: Everything You Ever Wanted to Know about Nurture Strea...
 

Mehr von MLconf

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...MLconf
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingMLconf
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...MLconf
 
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushIgor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushMLconf
 
Josh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceJosh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceMLconf
 
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...MLconf
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...MLconf
 
Meghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMeghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMLconf
 
Noam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionNoam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionMLconf
 
June Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLJune Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLMLconf
 
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksSneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksMLconf
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...MLconf
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldMLconf
 
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...MLconf
 
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...MLconf
 
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...MLconf
 
Neel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeNeel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeMLconf
 
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...MLconf
 
Soumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareSoumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareMLconf
 
Roy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesRoy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesMLconf
 

Mehr von MLconf (20)

Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
Jamila Smith-Loud - Understanding Human Impact: Social and Equity Assessments...
 
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language UnderstandingTed Willke - The Brain’s Guide to Dealing with Context in Language Understanding
Ted Willke - The Brain’s Guide to Dealing with Context in Language Understanding
 
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
Justin Armstrong - Applying Computer Vision to Reduce Contamination in the Re...
 
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold RushIgor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
Igor Markov - Quantum Computing: a Treasure Hunt, not a Gold Rush
 
Josh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious ExperienceJosh Wills - Data Labeling as Religious Experience
Josh Wills - Data Labeling as Religious Experience
 
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
Vinay Prabhu - Project GaitNet: Ushering in the ImageNet moment for human Gai...
 
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
Jekaterina Novikova - Machine Learning Methods in Detecting Alzheimer’s Disea...
 
Meghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the CheapMeghana Ravikumar - Optimized Image Classification on the Cheap
Meghana Ravikumar - Optimized Image Classification on the Cheap
 
Noam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data CollectionNoam Finkelstein - The Importance of Modeling Data Collection
Noam Finkelstein - The Importance of Modeling Data Collection
 
June Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of MLJune Andrews - The Uncanny Valley of ML
June Andrews - The Uncanny Valley of ML
 
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection TasksSneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
Sneha Rajana - Deep Learning Architectures for Semantic Relation Detection Tasks
 
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
Anoop Deoras - Building an Incrementally Trained, Local Taste Aware, Global D...
 
Vito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI WorldVito Ostuni - The Voice: New Challenges in a Zero UI World
Vito Ostuni - The Voice: New Challenges in a Zero UI World
 
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
Anna choromanska - Data-driven Challenges in AI: Scale, Information Selection...
 
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
Janani Kalyanam - Machine Learning to Detect Illegal Online Sales of Prescrip...
 
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
Esperanza Lopez Aguilera - Using a Bayesian Neural Network in the Detection o...
 
Neel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to codeNeel Sundaresan - Teaching a machine to code
Neel Sundaresan - Teaching a machine to code
 
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
Rishabh Mehrotra - Recommendations in a Marketplace: Personalizing Explainabl...
 
Soumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better SoftwareSoumith Chintala - Increasing the Impact of AI Through Better Software
Soumith Chintala - Increasing the Impact of AI Through Better Software
 
Roy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime ChangesRoy Lowrance - Predicting Bond Prices: Regime Changes
Roy Lowrance - Predicting Bond Prices: Regime Changes
 

Kürzlich hochgeladen

CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Zilliz
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontologyjohnbeverley2021
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWERMadyBayot
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Victor Rentea
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusZilliz
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Angeliki Cooney
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsNanddeep Nachan
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native ApplicationsWSO2
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2
 

Kürzlich hochgeladen (20)

CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering Developers
 

Ewa Dominowska, Engineering Manager, Facebook at MLconf SEA - 5/20/16

  • 1.
  • 2. Generating a Billion Personal News Feeds Lessons Learned from News Feed Ranking Ewa Dominowska
  • 3. 1 News Feed Overview 2 Machine Learning in News Feed 3 Measurement
  • 4. What is Facebook News Feed? Way to connect with stories that matter to you most Connect, Inform and Entertain News Feed is the constantly updating list of stories in the middle of your home page or mobile app. News Feed includes status updates, photos, videos, links, app activity and likes from people, pages and groups that you follow on Facebook. Feed Ranking is just a tool, you are in control of what you see in your News Feed and can adjust your settings.
  • 5. ▪ Over 1,000,000,000 daily users ▪ Hundreds of billions stories seen per day ▪ Trillions of stories ranked per day ▪ Publish -> In Feed < 1s ▪ Retrieval + rank time < 200ms Basic Stats Alex Chapel Francis McDonough Victoria Beckchen
  • 6. Deliver everything that matters to people and nothing that doesn't ▪ Don’t miss any important stories ▪ New stories should show up within seconds ▪ Put the best content at the top ▪ People notice/interact with content at the top first. ▪ Better content at top means better experience, less good content missed. ▪ It’s not just winner takes all ordering of content matters
  • 7. How News Feed Works? Story 1 PHOTO Story 2 FRIEND POST Story 3 VIDEO Story 4 LINK SHARE Story 5 PHOTO Story 6 LINK SHARE Story 7 FRIEND POST ▪ Goal is to put best content on top ▪ Solution – every time you visit we rank all new content and put on top ▪ Anything you haven’t seen is new to you ▪ New friend shares same link you’ve seen ▪ Unseen old stories ▪ Seen stories with new comments ▪ For frequent users ranking is almost chronological ▪ Diversity of content matters 9:00 AM 1.9 1.1 0.8 0.6 0.4 0.3 0.4 Story 4 LINK SHARE Story 5 PHOTO Story 6 LINK SHARE Story 7 FRIEND POST 0.9 0.6 0.3 0.2 Story 8 PAGE POST Story 3 F_comment 1.0 1.3 10:00 AM Story 5 PHOTO 0.1 0.9 Story 9 VIDEO 10:10 AM Story 10 FRIEND POST 1.8 Story 11 LINK SHARE 1.5 Story 12 FRIEND POST 1.1 Story 13 VIDEO 0.2 12:00 PM
  • 9. Scoring based Ranking ▪ Given a potential feed story, how good is it? ▪ Express as probability of click, like, comment, etc. ▪ Assign different weights to different events, according to significance ▪ Example: close coworker feels earthquake ▪ Highest chance of click ▪ Decent chance of like/comment Event Probability Value* Click 5.1% 1 Like 2.9% 5 Comment 0.55% 20 Share 0.00005% 40 Friend 0.00003% 50 Hide 0.00002% -100 Total 0.306 *Example, not real values
  • 10. ▪ Why this structure: ▪ Uses Machine Learning to predict true, measurable behavior ▪ Models train on their own data ▪ Allows fast iteration ▪ Allows distributed development ▪ Allows for easy ranking of heterogeneous content ▪ Allows for value to be adjusted independently ▪ WORKS WELL IN PRACTICE Learnings
  • 11. Role of Network Structure ▪ News Feed delivers content from friends along social network ▪ Understanding the network is key to defining quality ▪ Who are your close friends? ▪ Whose photos do you always like? ▪ Whose links are the most interesting to you? Click Like Comment Weighted Sum Joe 0.012 0.0042 0.00082 0.0494 Susan 0.023 0.02 0.0082 0.287 Li 0.012 0.0037 0.001 0.0505 0.287 0.0494 0.0505 Joe Susan Li
  • 12. Feature Selection (BDTs) ▪ Start with over >100K potential (dense) features and all historical activity ▪ First, prune these to top ~2K ▪ Training time is proportional to number of examples * number of features ▪ Under-sample negative examples (impressions, no action) to help with # of examples ▪ Start with 100K features, max rows, keep most important 10K, train 10x rows ▪ Do this for each feed event type: train many forests ▪ Historical counts and propensity are some of the strongest features
  • 13. Model Training (Logistic regression) ▪ We need to react quickly and incorporate new content - use a simple model ▪ Logistic regression is simple, fast and easy to distribute ▪ Treat the trees as feature transforms, each one turning the input features into a set of categorical features, one per tree. ▪ Use logistic regression for online learning to quickly re-learn leaf weights F3 -0.1 0.3 0.2 F1 -0.5 0.2 -.05 F2 F3 Throw out boosted tree weights, use only transforms Input: (F1, F2, F3) Output (T1, T2) where T1  {Leaves of tree 1}
  • 14. Stacking: Combined Tree + LR Model ▪ Main Advantage: Tree application is computationally expensive and slow ▪ Reuse click tree to predict likes, comments, etc. ▪ Only slightly more expensive than independent models; better prediction performance – transfer learnings ~Thousands of Raw features Thousands of Tree Transforms Sparse Boolean features + non-tree raw features Like Comment Share Friend Outbound Click Follow HideClick Click Like Comment Share Friend Outbound click Follow Hide
  • 15. Other models + sparse features ▪ Train Neural nets to predict events ▪ Discard final layer, use final layer outputs as features ▪ Add sparse features such as text or content ID Raw Features Forest Raw Features Neural Network Sparse features Logistic Regression Like Comment Share Hide Outbound Click Fan | Follow FriendClick
  • 16. ▪ Data freshness matters – simple models allows for online learning and twitch response ▪ Feature generation is part of the modeling process ▪ Stacking ▪ supports plugging-in new algorithms and features easily ▪ works very well in practice ▪ Use skewed sampling to manage high data volumes ▪ Historical counters as features provides highly predictive features, easy to update online Learnings
  • 18. Measurement 18 ▪ Selecting the right objective function ▪ Defining metrics ▪ Implicit: Engagement, ex. Click ▪ Longitudinal metrics, ex. Abandonment ▪ Explicit: Quality, ex. Survey Score
  • 19. Why are implicit metrics limited? ▪ Some important stories don’t get that much engagement ▪ Eg. Sad stories and world news ▪ Some lower quality stories get lots of engagement, social expectations ▪ Relative importance: Is comment always more important then a like? ▪ Goal is to align ranking with personalized relevance ▪ Solution -> Ask users directly: Collect explicit signals from survey data
  • 20. Pairwise Comparison Survey 20 ▪ Pair wise comparison between two stories from same feed. ▪ Pro: Real user preference on two stories from same query. ▪ Con: Don’t really know if they are just comparing two good stories, or two poor stories or one of each.
  • 21. In or Out survey 21 ▪ Single Story survey, “do you want to see it or not?” ▪ Pro: Fun, simple, absolute ▪ Con: People do not really know the consequence of the action, limited resolution does not help with ranking
  • 22. Rating Survey 22 ▪ 5pt rating scale, “how much do you want to see the story in your feed?”. ▪ Pro: Absolute metrics, good participant rate. ▪ Con: Out of context, raters might not be truthful, harder to do for users.
  • 23. In-Context Survey 23 ▪ 5pt rating scale, “how much do you want to see the story in your feed?”. ▪ Pro: In context ▪ Con: Can distract, lead to abandonment, takes up valuable real-estate from the feed
  • 24. Absolute vs. relative ratings ▪ Relative ▪ Easier ▪ Infinite precision ▪ More self-consistent ▪ More calibrated cross people ▪ Absolute ▪ Gives amount of delta ▪ No intransitivity issues ▪ Clear definition of best ▪ Which one do we choose? ▪ Solution: Do both
  • 25. Start to better understand what matters for each individual 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Definitely do NOT want to see this in Feed Do not want to see in Feed Don't mind seeing in Feed but wouldn't mind missing either Want to see in Feed Definitely want to see in feed Someone you really don't care about Someone you don't care about Someone you somewhat care about Someone you care about Someone you really care about
  • 26. Improving Feed based on rating results ▪ Not enough data to do large scale, personalized machine learning ▪ Look for other insights ▪ Eg. How much should we value a comment vs. a like ▪ Ranking by α p(like) + β p(comment) ▪ Optimal α, β depends on content type, content creator, context ▪ Passive consumption (dwell time) prediction improves relevance ▪ Response means different things in different contexts and for different people ▪ Eg: ‘like’ is harder to come by on public content than friend content, and hence tends to indicate higher quality there. P(like)P(outboundclick) Rating vs. p(like) and p(outbound click) Avg.Rating
  • 27. Learnings ▪ Both implicit and explicit signals are important and can be used together ▪ Multiple survey types can be used simultaneously to get different advantages ▪ Metrics are important - the right metrics are needed to define an objective function for our models and to measure model performance ▪ ML and Metrics are tools that let us CONNECT, INFORM and ENTERTAIN Facebook users.
  • 28. We far from done… Come join us to help solve the next big challenge

Hinweis der Redaktion

  1. Trade offs
  2. What is Facebook News Feed? Show you content you care about most Constantly updating list of stories: status updates, videos, links, comments and likes from people, pages and groups that you follow. Influenced by your connections and activities -> goal is to help connect, inform and entertain our users. Tools for control for people – following & friending, Unfollowing, Hiding, See first The stories that show in your News Feed are influenced by your connections and activity on Facebook. This helps you to see more stories that interest you from friends you interact with the most.
  3. What are some basic stats? Nothing gets scored until a user visits the feed, then we have less then 200ms to retrieve, score and rank all content
  4. What is the value add? Too much content and not enough time The feed must be completely personalized but still highly engaging to Facebook’s users so they’ll keep coming back and seeing more Feed helps organize all the content. Better content on top Ordering matters Engagement is a proxy of what you might want to see: Signals used: who posted, what kind of content, how many interactions, when the post was created
  5. How News Feed Works? Rank all new content and put on top 9am: 7 new stories, ranked specifically for you using a relevance score -> See 3, interact with 1 10am: what you’ve seen gets pushed down, 8 brand new, 3 has a new friend comment, 4-7 were unseen, scoring changes, now story 7 – friend post ranked higher, all scores adjusted based on context, see stories 8,3,7,4,6 and comment on 4 10:10am: (not much new content) 9 brand new, and 5 unseen (new scores) 12:00pm: 4 new stories, friend and link stories ranked higher, friend stories not adjacent
  6. Since stories are ordered based on a score. How do we compute the relevance score? Sum(Observed behaviors*Significance of each behavior)
  7. Why structure the problem as ranking by sum of weighted, predicted behavior? Well defined objective function, ML used to predict measurable behavior Models are trained on their own data Fast iteration Distributed development Heterogeneous content -> calibration is simplified Value can be adjusted independently -> Works well in practice
  8. What is the role of the network structure? How close you are to a person is an increasingly important metric, as judged by how often you like their posts, write on their Timeline, click through their photos. Reflects explicit preferences made by the user (links are connections formed by friending a person, joining a group or following a page) Links get strengthened through ongoing implicit actions: click, like, comment Joe, Susan and Li are all Wei’s friends. Susan interacts with Wei’s posts a lot more so it’s more likely to see his posts ranked higher. Social network signals and historical engagement are some of the most predictive features
  9. What data and features do we used to build a model? How do we select the right features? Start is > 100K features, prune to top 2K for efficiency Trillions of examples (train on the right data, subsample negative examples)
  10. What model do we use for prediction? Simple, fast to predict, fast to update, easy to distribute and debug -> Logistic regression
  11. Why this structure? Trees and expensive and slow but help select the best features Each model is train on own data but learning can be transferred by re-using trees Works well with very large amount of data and large number of features
  12. Why BDTs and Logistic regression? Empirically we have found these two to work well, but this learning structure supports easy way to plug in new algorithms We are now also using Neural Nets and untransformed sparse features
  13. What have we learned so far? Online learning to have good predictions for new content < 1s Using BDTs as a tool for feature selection Stacking: able to use both simple and complex models on large data with high performance, and modular architecture allows for trying new things and quick iteration Skewed sampling helps manage large data volumes Historical counters (over different time-ranges) are highly predictive and easy to update
  14. How do we know if we are doing a good job? How do we define success?
  15. Why measurement matters? Selecting the right objective function is hard and important We look at what people do and what they say: Two types of metrics: implicit and explicit Online survey Experimentation We invest in controls for people
  16. Why are implicit metrics limited? They can be inconsistent, they vary by person and by content, how can we normalize?
  17. How do we collect explicit signals? We ask a representative sample of people through direct surveys. Type of surveys? RELATIVE comparison
  18. ABSOLUTE comparison
  19. Multi-scale absolute comparison Most common
  20. Multi-scale, absolute comparison in context
  21. Which survey type is better?
  22. Why is survey data useful? HQ pages vs. meme pages… Are a lot of these ad-like? What data do we have here that is useful?
  23. How can this data be used to improve ranking? Ranking by α p(like) + β p(comment)
  24. What have we learned so far? Both implicit and explicit signals are important and can be used together ML and Metrics are tools that let us CONECT, INFORM and ENTERNTAIN Facebook users.