SlideShare une entreprise Scribd logo
1  sur  40
Télécharger pour lire hors ligne
Copyright © 2016 Criteo
ML for Display Advertising @ Scale
Damien Lefortier
MLconf NYC
2016-04-15
Copyright © 2015 Criteo
Outline
• Introduction to the AdTech / Criteo
• Deep dive into our ML algorithms
• Offline and online evaluation
• Future areas of research
2
Copyright © 2015 Criteo
Outline
• Introduction to the AdTech / Criteo
• Deep dive into our ML algorithms
• Offline and online evaluation
• Future areas of research
3
Copyright © 2015 Criteo
AdTech / Criteo
4
Advertiser Publisher
Copyright © 2015 Criteo
Our Engine is trying to answer 3 questions
COMMON
OBJECTIVE:
Maximize the
client’s value
1. How much should we bid for a given ad space?
My company
yes no no
My company
yes …
2. What products should we recommend / show?
My company
BUY!
My company
BUY! BUY!
BUY! BUY!
My company
BUY! BUY!
BUY! BUY!
My company
BUY! BUY! BUY!
BUY!
3. What is the best look & feel of the banner?
Copyright © 2015 Criteo
6
Physical infrastructure
7 in-house data centers on 3 continents
~ 15000 servers; largest Hadoop cluster in Europe
More than 35 PB of data storage
Traffic
800k HTTP requests / sec (peak activity)
29000 impressions / sec (peak activity)
< 10 ms to process a bidding request
< 100 ms to render the ad (if we win)
Copyright © 2015 Criteo
Outline
• Introduction to the AdTech / Criteo
• Deep dive into our ML algorithms
• Offline and online evaluation
• Future areas of research
7
Copyright © 2015 Criteo
8
Bidding
•Should we bid?
•At which price?
Recommendation
•Which products should
we display?
Look & Feel
•Big image vs small image
•Background color, ...
Prediction
•Generic prediction engine
•Specific models trained on TBs of data
Copyright © 2015 Criteo
9
Bidding
•Should we bid?
•At which price?
Recommendation
•Which products should
we display?
Look & Feel
•Big image vs small image
•Background color, ...
Prediction
•Generic prediction engine
•Specific models trained on TBs of data
Copyright © 2015 Criteo
Bidding strategy (1)
• As we sell performance: Criteo’s and our clients’ interests are aligned.
• The cost of a display is lower and independent from the bid (2nd price or floor),
so we should bid the max value the client is willing to pay.
• We use adjustments for 1st price auctions.
10
Copyright © 2015 Criteo
Bidding strategy (2)
• This value depends on the predicted performance and the client’s objective.
• Some examples:
• Click optimized campaign: bid = maxCPC  pClick
• CR optimized campaign: bid = maxCPO  pCR
• …
11
We train our prediction models on our historical displays
Historical displays
Variables
 Level of engagement of the user
 Quality of inventory
 User fatigue
 For travel: time to check-in and number
of nights
: clicked displays : converted displays (size = order value)
Our ability to predict relies
greatly on the relevance of
the variables we consider
Machine Learning
Algorithms
Copyright © 2015 Criteo
13
Bidding
•Should we bid?
•At which price?
Recommendation
•Which products should
we display?
Look & Feel
•Big image vs small image
•Background color, ...
Prediction
•Generic prediction engine
•Specific models trained on TBs of data
Copyright © 2015 Criteo
Recommend products for a user
• What we want: reco(user) = products
• 1B users x 3B products!
• But we need to scale and keep it fresh
• What we can do:
Pre-select products offline
Refine scoring online to get final candidates
Bob saw orange shoes
Some candidate products
Historical
Similar
Complementary
Most viewed
Products delivering the best performance are displayed
Variables
 Products seen by the user
 Time since product event
 Level of similarity
 Product features
Historical displays
: clicked products : converted products (size = order value)
Products are selected based
on their CTR, CR or OV
Machine Learning
Algorithms
Copyright © 2015 Criteo
17
Bidding
•Should we bid?
•At which price?
Recommendation
•Which products should
we display?
Look & Feel
•Big image vs small image
•Background color, ...
Prediction
•Generic prediction engine
•Specific models trained on TBs of data
Historical displays (color = look & feel)
We train our prediction models on our historical displays
Variables
Some of which we control:
 How user interacts with banner
 Organization of information
 Colorset
Some of which we don’t:
 Zone format
 Publisher
: clicked displays : converted displays (size = order value)
Look and feel will be selected
based on its CTR, CR or OV
My company
BUY! BUY! BUY!
BUY!
Machine Learning
Algorithms
Copyright © 2015 Criteo
19
Bidding
•Should we bid?
•At which price?
Recommendation
•Which products should
we display?
Look & Feel
•Big image vs small image
•Background color, ...
Prediction
•Generic prediction engine
•Specific models trained on TBs of data
Copyright © 2015 Criteo
Many models to learn
• We have different ML models for bidding / recommendation / … and depending
on the campaign objective. We use logistic regression in many places.
• Each model is trained independently & refreshed as often as possible.
• Three main sources of features: user, ad, page (mostly categorical).
20
Copyright © 2015 Criteo
Learn on huge volumes of data
10 000 displays
Copyright © 2015 Criteo
Learn on huge volumes of data
10 000 displays
leads to
50 clicks
Copyright © 2015 Criteo
Learn on huge volumes of data
10 000 displays
leads to
50 clicks
leads to
1 sale
Copyright © 2015 Criteo
Quadratic features
• Outer product between 2 features (similar to a polynomial kernel of degree 2).
• Example between site and advertiser:
24
Publisher network
Publisher
Site
Url
Advertiser network
Ad
Campaign
Advertiser
Copyright © 2015 Criteo
Hashing trick
• Standard representation of categorical features: “one-hot” encoding
• Dimensionality equal to the number of different values…
• Hashing to reduce dimensionality (made popular by John Langford in VW)
• Dimensionality now independent of number of values
• Using:
25
Copyright © 2015 Criteo
In-house Machine Learning library -- IRMA
• We have our own large-scale distributed machine learning library on top of
Hadoop used for all our models.
• From a ML perspective we rely, in most cases, on an L-BFGS solver initialized
with SGD (see, eg, A. Agarwal et al. A Reliable Effective Terascale Linear
Learning System).
26
Copyright © 2015 Criteo
Distribution of L-BFGS & SGD
• L-BFGS, being a batch algorithm, is easy to distribute.
• SGD is a bit tricker: we do parameter averaging for that and we also use
Hogwild! to multi-thread on each machine.
• We use Hadoop AllReduce:
27
Copyright © 2015 Criteo
A word on more advanced techniques
• Irma is not only about vanilla logistic regression with L2 regularization… 
• It contains more advanced techniques such as, e.g., transfer learning,
factorization machines, learning to rank, cost-sensitive learning, …
• We for example use cost-sensitive learning for bidding.
28
Copyright © 2015 Criteo
Outline
• Introduction to the AdTech / Criteo
• Deep dive into our ML algorithms
• Offline and online evaluation
• Future areas of research
29
Copyright © 2015 Criteo
Offline & online evaluation
Usual two-step process:
• Offline testing is fast, cheap, and efficient for wide exploration.
• Online testing is expensive but has the ultimate word.
30
Copyright © 2015 Criteo
Offline metrics (bidding case)
• We use classical metrics: LLH, RMSE, … (which focus on the prediction and
ignore the bidding system where we use these models).
• Utility from Offline Evaluation of Response Prediction in Online Advertising
Auctions by O. Chapelle (WWW’15).
31
Copyright © 2015 Criteo
Online metrics (bidding case)
• RevExTac = Revenue Excluding Traffic Acquisition Costs
• Cost, Revenue, …
32
Copyright © 2015 Criteo
Some statistics on evaluation
• 100K+ offline tests per year
• 1K+ A/B tests per year
• Many people 
33
• We developed a platform and processes that enable very fast testing and improvement
Copyright © 2015 Criteo
Outline
• Introduction to the AdTech / Criteo
• Deep dive into our ML algorithms
• Offline and online evaluation
• Future areas of research
34
Copyright © 2015 Criteo
Some examples of future areas of Research
• Counterfactual evaluation (offline A/B tests)
• Embeddings for recommandation
• Policy learning
35
Copyright © 2015 Criteo
Counterfactual evaluation
• Estimate the business metric directly (clicks, sales, …).
• Using the production model + randomization.
• Good results on clicks already.
36
Copyright © 2015 Criteo
Embeddings for recommandation
• Can embeddings (for example a la word2vec) help us compute similarities
between, e.g., different products or users?
37
Copyright © 2015 Criteo
Policy learning – example on Look & Feel optimization
• Classical supervised machine learning approach: learn a pClick model and
sort by predicted values for each possible value (e.g, each color).
• This is a hard problem and may be overkill!
• Really, we only want to know which color is the best according to some
business metric (eg, sales).
38
Copyright © 2015 Criteo
Academic research @ Criteo
• Our 1st public dataset is online: http://bit.ly/1vgw2XC
• New 1TB dataset released last year.
• Some recent publications:
Offline Evaluation of Response Prediction in Online Advertising Auctions. O. Chapelle, WWW’15.
Sources of Variability in Large-scale Machine Learning Systems. D. Lefortier, A. Truchet, and M. de
Rijke, NIPS 2015, workshop on ML systems, 2015.
Cost-sensitive Learning for Bidding in Online Advertising Auctions. F. Vasile and D. Lefortier, NIPS
workshop on ML for e-Commerce, 2015.
39
Copyright © 2015 Criteo
Questions
d.lefortier@criteo.com

Contenu connexe

Tendances

Criteo's Ad Week 2012 presentation - Big Data and the Value of Clickers
Criteo's Ad Week 2012 presentation - Big Data and the Value of ClickersCriteo's Ad Week 2012 presentation - Big Data and the Value of Clickers
Criteo's Ad Week 2012 presentation - Big Data and the Value of ClickersCriteo
 
Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...
Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...
Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...Digiday
 
Criteo - NOAH13 London
Criteo - NOAH13 LondonCriteo - NOAH13 London
Criteo - NOAH13 LondonNOAH Advisors
 
Ad Server Solutions - ad server ad exchange
Ad Server Solutions - ad server ad exchangeAd Server Solutions - ad server ad exchange
Ad Server Solutions - ad server ad exchangeAd Server Solutions
 
Essent - Using AI@Scale to drive a seamless customer experience
Essent - Using AI@Scale to drive a seamless customer experienceEssent - Using AI@Scale to drive a seamless customer experience
Essent - Using AI@Scale to drive a seamless customer experienceBBP
 
3 Minute Introduction
3 Minute Introduction3 Minute Introduction
3 Minute IntroductionJulian Tol
 
Snowplow at Sigfig
Snowplow at SigfigSnowplow at Sigfig
Snowplow at Sigfigyalisassoon
 
The Better Programmatic Experience
The Better Programmatic ExperienceThe Better Programmatic Experience
The Better Programmatic ExperienceMediaPost
 
When business meets measurement protocol - atdconf - 2017 - Tel Aviv
When business meets measurement protocol - atdconf - 2017 - Tel AvivWhen business meets measurement protocol - atdconf - 2017 - Tel Aviv
When business meets measurement protocol - atdconf - 2017 - Tel AvivZorin Radovancevic
 
Obtaining the Programmatic Holy Grail: Transparency, Flexibility & Control
Obtaining the Programmatic Holy Grail: Transparency, Flexibility & ControlObtaining the Programmatic Holy Grail: Transparency, Flexibility & Control
Obtaining the Programmatic Holy Grail: Transparency, Flexibility & ControlMediaPost
 
Using Programmatic to Reach People in the Moments that Matter
Using Programmatic to Reach People in the Moments that MatterUsing Programmatic to Reach People in the Moments that Matter
Using Programmatic to Reach People in the Moments that MatterIncubeta NMPi
 
What You Need To Know For A Successful Start on DoubleClick Bid Manager
What You Need To Know For A Successful Start on DoubleClick Bid ManagerWhat You Need To Know For A Successful Start on DoubleClick Bid Manager
What You Need To Know For A Successful Start on DoubleClick Bid ManagerHanapin Marketing
 
Programmatic Advertising: How To Join In On the Fun
Programmatic Advertising: How To Join In On the FunProgrammatic Advertising: How To Join In On the Fun
Programmatic Advertising: How To Join In On the FunHanapin Marketing
 

Tendances (13)

Criteo's Ad Week 2012 presentation - Big Data and the Value of Clickers
Criteo's Ad Week 2012 presentation - Big Data and the Value of ClickersCriteo's Ad Week 2012 presentation - Big Data and the Value of Clickers
Criteo's Ad Week 2012 presentation - Big Data and the Value of Clickers
 
Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...
Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...
Aligning with Buyers to Maximize Mobile Revenue presentation by Criteo at DPS...
 
Criteo - NOAH13 London
Criteo - NOAH13 LondonCriteo - NOAH13 London
Criteo - NOAH13 London
 
Ad Server Solutions - ad server ad exchange
Ad Server Solutions - ad server ad exchangeAd Server Solutions - ad server ad exchange
Ad Server Solutions - ad server ad exchange
 
Essent - Using AI@Scale to drive a seamless customer experience
Essent - Using AI@Scale to drive a seamless customer experienceEssent - Using AI@Scale to drive a seamless customer experience
Essent - Using AI@Scale to drive a seamless customer experience
 
3 Minute Introduction
3 Minute Introduction3 Minute Introduction
3 Minute Introduction
 
Snowplow at Sigfig
Snowplow at SigfigSnowplow at Sigfig
Snowplow at Sigfig
 
The Better Programmatic Experience
The Better Programmatic ExperienceThe Better Programmatic Experience
The Better Programmatic Experience
 
When business meets measurement protocol - atdconf - 2017 - Tel Aviv
When business meets measurement protocol - atdconf - 2017 - Tel AvivWhen business meets measurement protocol - atdconf - 2017 - Tel Aviv
When business meets measurement protocol - atdconf - 2017 - Tel Aviv
 
Obtaining the Programmatic Holy Grail: Transparency, Flexibility & Control
Obtaining the Programmatic Holy Grail: Transparency, Flexibility & ControlObtaining the Programmatic Holy Grail: Transparency, Flexibility & Control
Obtaining the Programmatic Holy Grail: Transparency, Flexibility & Control
 
Using Programmatic to Reach People in the Moments that Matter
Using Programmatic to Reach People in the Moments that MatterUsing Programmatic to Reach People in the Moments that Matter
Using Programmatic to Reach People in the Moments that Matter
 
What You Need To Know For A Successful Start on DoubleClick Bid Manager
What You Need To Know For A Successful Start on DoubleClick Bid ManagerWhat You Need To Know For A Successful Start on DoubleClick Bid Manager
What You Need To Know For A Successful Start on DoubleClick Bid Manager
 
Programmatic Advertising: How To Join In On the Fun
Programmatic Advertising: How To Join In On the FunProgrammatic Advertising: How To Join In On the Fun
Programmatic Advertising: How To Join In On the Fun
 

En vedette

Introduction Criteo - 2.0
Introduction Criteo - 2.0Introduction Criteo - 2.0
Introduction Criteo - 2.0Scott Turecek
 
RecsysFR: Criteo presentation
RecsysFR: Criteo presentationRecsysFR: Criteo presentation
RecsysFR: Criteo presentationrecsysfr
 
C# development workflow @ criteo
C# development workflow @ criteoC# development workflow @ criteo
C# development workflow @ criteoIbrahim Abubakari
 
Response prediction for display advertising - WSDM 2014
Response prediction for display advertising - WSDM 2014Response prediction for display advertising - WSDM 2014
Response prediction for display advertising - WSDM 2014Olivier Chapelle
 
InMobi Webinar: 2014 - Moving Mobile to the Center
InMobi Webinar: 2014 - Moving Mobile to the CenterInMobi Webinar: 2014 - Moving Mobile to the Center
InMobi Webinar: 2014 - Moving Mobile to the CenterInMobi
 
AI in AdTech by Ruslan Shevchenko Tech Hangout #6
AI in AdTech by Ruslan Shevchenko  Tech Hangout #6AI in AdTech by Ruslan Shevchenko  Tech Hangout #6
AI in AdTech by Ruslan Shevchenko Tech Hangout #6Innovecs
 
Infographic: How Professional Services Automation can transform your Company!
Infographic: How Professional Services Automation can transform your Company!Infographic: How Professional Services Automation can transform your Company!
Infographic: How Professional Services Automation can transform your Company!Changepoint
 
Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2
Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2
Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2Paris Monitoring
 
[Materials];[Admicro tang hieu_suat_quang_cao]
[Materials];[Admicro tang hieu_suat_quang_cao][Materials];[Admicro tang hieu_suat_quang_cao]
[Materials];[Admicro tang hieu_suat_quang_cao]AiiM Education
 
Social Media power on Shoppers' decision journey
Social Media power on Shoppers' decision journeySocial Media power on Shoppers' decision journey
Social Media power on Shoppers' decision journeytrieuhn
 
Content Marketing - Make an Impression
Content Marketing - Make an ImpressionContent Marketing - Make an Impression
Content Marketing - Make an ImpressionMark Jamieson
 
Admicro mobileads profile 0946.251.335
Admicro mobileads profile 0946.251.335Admicro mobileads profile 0946.251.335
Admicro mobileads profile 0946.251.335Công Ngố New
 
Effects of hashtag in Instagram Marketing
Effects of hashtag in Instagram MarketingEffects of hashtag in Instagram Marketing
Effects of hashtag in Instagram MarketingHoà Bùi
 
InMobi Brand Evolution
InMobi Brand EvolutionInMobi Brand Evolution
InMobi Brand EvolutionInMobi
 
Etude Criteo - la valeur réelle des internautes qui cliquent - 26 Juin 2012
Etude Criteo - la valeur réelle des internautes qui cliquent  - 26 Juin 2012Etude Criteo - la valeur réelle des internautes qui cliquent  - 26 Juin 2012
Etude Criteo - la valeur réelle des internautes qui cliquent - 26 Juin 2012Romain Fonnier
 
Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...
Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...
Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...MongoDB
 
Remote 2 android - Poly sáng tạo 2016 - Sinh viên FPT Polytechnic
Remote 2 android - Poly sáng tạo 2016 - Sinh viên FPT PolytechnicRemote 2 android - Poly sáng tạo 2016 - Sinh viên FPT Polytechnic
Remote 2 android - Poly sáng tạo 2016 - Sinh viên FPT PolytechnicFPT Polytechnic
 

En vedette (20)

Introduction Criteo - 2.0
Introduction Criteo - 2.0Introduction Criteo - 2.0
Introduction Criteo - 2.0
 
RecsysFR: Criteo presentation
RecsysFR: Criteo presentationRecsysFR: Criteo presentation
RecsysFR: Criteo presentation
 
C# development workflow @ criteo
C# development workflow @ criteoC# development workflow @ criteo
C# development workflow @ criteo
 
Response prediction for display advertising - WSDM 2014
Response prediction for display advertising - WSDM 2014Response prediction for display advertising - WSDM 2014
Response prediction for display advertising - WSDM 2014
 
InMobi Webinar: 2014 - Moving Mobile to the Center
InMobi Webinar: 2014 - Moving Mobile to the CenterInMobi Webinar: 2014 - Moving Mobile to the Center
InMobi Webinar: 2014 - Moving Mobile to the Center
 
AI in AdTech by Ruslan Shevchenko Tech Hangout #6
AI in AdTech by Ruslan Shevchenko  Tech Hangout #6AI in AdTech by Ruslan Shevchenko  Tech Hangout #6
AI in AdTech by Ruslan Shevchenko Tech Hangout #6
 
Infographic: How Professional Services Automation can transform your Company!
Infographic: How Professional Services Automation can transform your Company!Infographic: How Professional Services Automation can transform your Company!
Infographic: How Professional Services Automation can transform your Company!
 
Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2
Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2
Bizarre... vous avez dit bizarre - Paris Monitoring meetup #2
 
Saintjo Two AV4
Saintjo Two AV4Saintjo Two AV4
Saintjo Two AV4
 
[Materials];[Admicro tang hieu_suat_quang_cao]
[Materials];[Admicro tang hieu_suat_quang_cao][Materials];[Admicro tang hieu_suat_quang_cao]
[Materials];[Admicro tang hieu_suat_quang_cao]
 
Social Media power on Shoppers' decision journey
Social Media power on Shoppers' decision journeySocial Media power on Shoppers' decision journey
Social Media power on Shoppers' decision journey
 
Content Marketing - Make an Impression
Content Marketing - Make an ImpressionContent Marketing - Make an Impression
Content Marketing - Make an Impression
 
Frnog26
Frnog26Frnog26
Frnog26
 
Admicro mobileads profile 0946.251.335
Admicro mobileads profile 0946.251.335Admicro mobileads profile 0946.251.335
Admicro mobileads profile 0946.251.335
 
Effects of hashtag in Instagram Marketing
Effects of hashtag in Instagram MarketingEffects of hashtag in Instagram Marketing
Effects of hashtag in Instagram Marketing
 
InMobi Brand Evolution
InMobi Brand EvolutionInMobi Brand Evolution
InMobi Brand Evolution
 
Etude Criteo - la valeur réelle des internautes qui cliquent - 26 Juin 2012
Etude Criteo - la valeur réelle des internautes qui cliquent  - 26 Juin 2012Etude Criteo - la valeur réelle des internautes qui cliquent  - 26 Juin 2012
Etude Criteo - la valeur réelle des internautes qui cliquent - 26 Juin 2012
 
Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...
Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...
Morning with MongoDB Paris 2012 - Cas d'usages courant en entreprise. Présent...
 
FTI Intro
FTI IntroFTI Intro
FTI Intro
 
Remote 2 android - Poly sáng tạo 2016 - Sinh viên FPT Polytechnic
Remote 2 android - Poly sáng tạo 2016 - Sinh viên FPT PolytechnicRemote 2 android - Poly sáng tạo 2016 - Sinh viên FPT Polytechnic
Remote 2 android - Poly sáng tạo 2016 - Sinh viên FPT Polytechnic
 

Similaire à Damien Lefortier, Senior Machine Learning Engineer and Tech Lead in the Prediction Machine Learning team, Criteo at MLconf NYC - 4/15/16

Machine Learning for Performance Advertising
Machine Learning for Performance AdvertisingMachine Learning for Performance Advertising
Machine Learning for Performance AdvertisingEustache Diemert
 
Recommendation at scale
Recommendation at scaleRecommendation at scale
Recommendation at scalesimondolle
 
Unifying Marketing Data & Multi-Touch Attribution Analysis
Unifying Marketing Data & Multi-Touch Attribution AnalysisUnifying Marketing Data & Multi-Touch Attribution Analysis
Unifying Marketing Data & Multi-Touch Attribution AnalysisPrinciple America
 
CyberLab Development Division
CyberLab Development Division CyberLab Development Division
CyberLab Development Division Vivek chan
 
Adobe Business.pptx
Adobe Business.pptxAdobe Business.pptx
Adobe Business.pptxAnkush Kapil
 
Unlocking Scale Through Pricing
Unlocking Scale Through PricingUnlocking Scale Through Pricing
Unlocking Scale Through PricingOpenView
 
Isv cloud business readiness assessment
Isv cloud business readiness assessmentIsv cloud business readiness assessment
Isv cloud business readiness assessmentMIS
 
RecSys 2015: Large-scale real-time product recommendation at Criteo
RecSys 2015: Large-scale real-time product recommendation at CriteoRecSys 2015: Large-scale real-time product recommendation at Criteo
RecSys 2015: Large-scale real-time product recommendation at CriteoRomain Lerallut
 
Search Engine Marketing 101 For Techstars Chicago 2017
Search Engine Marketing 101 For Techstars Chicago 2017Search Engine Marketing 101 For Techstars Chicago 2017
Search Engine Marketing 101 For Techstars Chicago 2017Elan Mosbacher
 
Marketing automation solutions webinar (part 2)
Marketing automation solutions webinar (part 2)Marketing automation solutions webinar (part 2)
Marketing automation solutions webinar (part 2)Acquisio
 
Programmatic Overview and Best Practices
Programmatic Overview and Best PracticesProgrammatic Overview and Best Practices
Programmatic Overview and Best PracticesOperative
 
3 Tactics for UA Success in 2017 and 2018
3 Tactics for UA Success in 2017 and 20183 Tactics for UA Success in 2017 and 2018
3 Tactics for UA Success in 2017 and 2018Eric Seufert
 
Simon Dollé_Large-scale Real-time recommendation at Criteo
Simon Dollé_Large-scale Real-time recommendation at Criteo Simon Dollé_Large-scale Real-time recommendation at Criteo
Simon Dollé_Large-scale Real-time recommendation at Criteo Dataconomy Media
 
Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...
Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...
Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...Databricks
 
3 Challenges of Building Complex Dashboards with Open Source Components
3 Challenges of Building Complex Dashboards with Open Source Components3 Challenges of Building Complex Dashboards with Open Source Components
3 Challenges of Building Complex Dashboards with Open Source ComponentsRyan MacCarrigan
 
How to Wrangle Data for Machine Learning on AWS
 How to Wrangle Data for Machine Learning on AWS How to Wrangle Data for Machine Learning on AWS
How to Wrangle Data for Machine Learning on AWSAmazon Web Services
 
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...Alok Singh
 
Tech Job Conference: Software Engineer @Criteo
Tech Job Conference: Software Engineer @CriteoTech Job Conference: Software Engineer @Criteo
Tech Job Conference: Software Engineer @CriteoGilles Legoux
 
Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...
Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...
Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...Daniel Caridi
 
CompeteWorkshop_ALLSLIDESv2
CompeteWorkshop_ALLSLIDESv2CompeteWorkshop_ALLSLIDESv2
CompeteWorkshop_ALLSLIDESv2Adam Hecht
 

Similaire à Damien Lefortier, Senior Machine Learning Engineer and Tech Lead in the Prediction Machine Learning team, Criteo at MLconf NYC - 4/15/16 (20)

Machine Learning for Performance Advertising
Machine Learning for Performance AdvertisingMachine Learning for Performance Advertising
Machine Learning for Performance Advertising
 
Recommendation at scale
Recommendation at scaleRecommendation at scale
Recommendation at scale
 
Unifying Marketing Data & Multi-Touch Attribution Analysis
Unifying Marketing Data & Multi-Touch Attribution AnalysisUnifying Marketing Data & Multi-Touch Attribution Analysis
Unifying Marketing Data & Multi-Touch Attribution Analysis
 
CyberLab Development Division
CyberLab Development Division CyberLab Development Division
CyberLab Development Division
 
Adobe Business.pptx
Adobe Business.pptxAdobe Business.pptx
Adobe Business.pptx
 
Unlocking Scale Through Pricing
Unlocking Scale Through PricingUnlocking Scale Through Pricing
Unlocking Scale Through Pricing
 
Isv cloud business readiness assessment
Isv cloud business readiness assessmentIsv cloud business readiness assessment
Isv cloud business readiness assessment
 
RecSys 2015: Large-scale real-time product recommendation at Criteo
RecSys 2015: Large-scale real-time product recommendation at CriteoRecSys 2015: Large-scale real-time product recommendation at Criteo
RecSys 2015: Large-scale real-time product recommendation at Criteo
 
Search Engine Marketing 101 For Techstars Chicago 2017
Search Engine Marketing 101 For Techstars Chicago 2017Search Engine Marketing 101 For Techstars Chicago 2017
Search Engine Marketing 101 For Techstars Chicago 2017
 
Marketing automation solutions webinar (part 2)
Marketing automation solutions webinar (part 2)Marketing automation solutions webinar (part 2)
Marketing automation solutions webinar (part 2)
 
Programmatic Overview and Best Practices
Programmatic Overview and Best PracticesProgrammatic Overview and Best Practices
Programmatic Overview and Best Practices
 
3 Tactics for UA Success in 2017 and 2018
3 Tactics for UA Success in 2017 and 20183 Tactics for UA Success in 2017 and 2018
3 Tactics for UA Success in 2017 and 2018
 
Simon Dollé_Large-scale Real-time recommendation at Criteo
Simon Dollé_Large-scale Real-time recommendation at Criteo Simon Dollé_Large-scale Real-time recommendation at Criteo
Simon Dollé_Large-scale Real-time recommendation at Criteo
 
Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...
Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...
Yelp Ad Targeting at Scale with Apache Spark with Inaz Alaei-Novin and Joe Ma...
 
3 Challenges of Building Complex Dashboards with Open Source Components
3 Challenges of Building Complex Dashboards with Open Source Components3 Challenges of Building Complex Dashboards with Open Source Components
3 Challenges of Building Complex Dashboards with Open Source Components
 
How to Wrangle Data for Machine Learning on AWS
 How to Wrangle Data for Machine Learning on AWS How to Wrangle Data for Machine Learning on AWS
How to Wrangle Data for Machine Learning on AWS
 
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
 
Tech Job Conference: Software Engineer @Criteo
Tech Job Conference: Software Engineer @CriteoTech Job Conference: Software Engineer @Criteo
Tech Job Conference: Software Engineer @Criteo
 
Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...
Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...
Tech-Talk Tuesday: How to Develop and Grow Your Optimization Efforts Into a S...
 
CompeteWorkshop_ALLSLIDESv2
CompeteWorkshop_ALLSLIDESv2CompeteWorkshop_ALLSLIDESv2
CompeteWorkshop_ALLSLIDESv2
 

Plus de 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
 

Plus de 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
 

Dernier

08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsRoshan Dwivedi
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...gurkirankumar98700
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 

Dernier (20)

08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 

Damien Lefortier, Senior Machine Learning Engineer and Tech Lead in the Prediction Machine Learning team, Criteo at MLconf NYC - 4/15/16

  • 1. Copyright © 2016 Criteo ML for Display Advertising @ Scale Damien Lefortier MLconf NYC 2016-04-15
  • 2. Copyright © 2015 Criteo Outline • Introduction to the AdTech / Criteo • Deep dive into our ML algorithms • Offline and online evaluation • Future areas of research 2
  • 3. Copyright © 2015 Criteo Outline • Introduction to the AdTech / Criteo • Deep dive into our ML algorithms • Offline and online evaluation • Future areas of research 3
  • 4. Copyright © 2015 Criteo AdTech / Criteo 4 Advertiser Publisher
  • 5. Copyright © 2015 Criteo Our Engine is trying to answer 3 questions COMMON OBJECTIVE: Maximize the client’s value 1. How much should we bid for a given ad space? My company yes no no My company yes … 2. What products should we recommend / show? My company BUY! My company BUY! BUY! BUY! BUY! My company BUY! BUY! BUY! BUY! My company BUY! BUY! BUY! BUY! 3. What is the best look & feel of the banner?
  • 6. Copyright © 2015 Criteo 6 Physical infrastructure 7 in-house data centers on 3 continents ~ 15000 servers; largest Hadoop cluster in Europe More than 35 PB of data storage Traffic 800k HTTP requests / sec (peak activity) 29000 impressions / sec (peak activity) < 10 ms to process a bidding request < 100 ms to render the ad (if we win)
  • 7. Copyright © 2015 Criteo Outline • Introduction to the AdTech / Criteo • Deep dive into our ML algorithms • Offline and online evaluation • Future areas of research 7
  • 8. Copyright © 2015 Criteo 8 Bidding •Should we bid? •At which price? Recommendation •Which products should we display? Look & Feel •Big image vs small image •Background color, ... Prediction •Generic prediction engine •Specific models trained on TBs of data
  • 9. Copyright © 2015 Criteo 9 Bidding •Should we bid? •At which price? Recommendation •Which products should we display? Look & Feel •Big image vs small image •Background color, ... Prediction •Generic prediction engine •Specific models trained on TBs of data
  • 10. Copyright © 2015 Criteo Bidding strategy (1) • As we sell performance: Criteo’s and our clients’ interests are aligned. • The cost of a display is lower and independent from the bid (2nd price or floor), so we should bid the max value the client is willing to pay. • We use adjustments for 1st price auctions. 10
  • 11. Copyright © 2015 Criteo Bidding strategy (2) • This value depends on the predicted performance and the client’s objective. • Some examples: • Click optimized campaign: bid = maxCPC  pClick • CR optimized campaign: bid = maxCPO  pCR • … 11
  • 12. We train our prediction models on our historical displays Historical displays Variables  Level of engagement of the user  Quality of inventory  User fatigue  For travel: time to check-in and number of nights : clicked displays : converted displays (size = order value) Our ability to predict relies greatly on the relevance of the variables we consider Machine Learning Algorithms
  • 13. Copyright © 2015 Criteo 13 Bidding •Should we bid? •At which price? Recommendation •Which products should we display? Look & Feel •Big image vs small image •Background color, ... Prediction •Generic prediction engine •Specific models trained on TBs of data
  • 14. Copyright © 2015 Criteo Recommend products for a user • What we want: reco(user) = products • 1B users x 3B products! • But we need to scale and keep it fresh • What we can do: Pre-select products offline Refine scoring online to get final candidates
  • 15. Bob saw orange shoes Some candidate products Historical Similar Complementary Most viewed
  • 16. Products delivering the best performance are displayed Variables  Products seen by the user  Time since product event  Level of similarity  Product features Historical displays : clicked products : converted products (size = order value) Products are selected based on their CTR, CR or OV Machine Learning Algorithms
  • 17. Copyright © 2015 Criteo 17 Bidding •Should we bid? •At which price? Recommendation •Which products should we display? Look & Feel •Big image vs small image •Background color, ... Prediction •Generic prediction engine •Specific models trained on TBs of data
  • 18. Historical displays (color = look & feel) We train our prediction models on our historical displays Variables Some of which we control:  How user interacts with banner  Organization of information  Colorset Some of which we don’t:  Zone format  Publisher : clicked displays : converted displays (size = order value) Look and feel will be selected based on its CTR, CR or OV My company BUY! BUY! BUY! BUY! Machine Learning Algorithms
  • 19. Copyright © 2015 Criteo 19 Bidding •Should we bid? •At which price? Recommendation •Which products should we display? Look & Feel •Big image vs small image •Background color, ... Prediction •Generic prediction engine •Specific models trained on TBs of data
  • 20. Copyright © 2015 Criteo Many models to learn • We have different ML models for bidding / recommendation / … and depending on the campaign objective. We use logistic regression in many places. • Each model is trained independently & refreshed as often as possible. • Three main sources of features: user, ad, page (mostly categorical). 20
  • 21. Copyright © 2015 Criteo Learn on huge volumes of data 10 000 displays
  • 22. Copyright © 2015 Criteo Learn on huge volumes of data 10 000 displays leads to 50 clicks
  • 23. Copyright © 2015 Criteo Learn on huge volumes of data 10 000 displays leads to 50 clicks leads to 1 sale
  • 24. Copyright © 2015 Criteo Quadratic features • Outer product between 2 features (similar to a polynomial kernel of degree 2). • Example between site and advertiser: 24 Publisher network Publisher Site Url Advertiser network Ad Campaign Advertiser
  • 25. Copyright © 2015 Criteo Hashing trick • Standard representation of categorical features: “one-hot” encoding • Dimensionality equal to the number of different values… • Hashing to reduce dimensionality (made popular by John Langford in VW) • Dimensionality now independent of number of values • Using: 25
  • 26. Copyright © 2015 Criteo In-house Machine Learning library -- IRMA • We have our own large-scale distributed machine learning library on top of Hadoop used for all our models. • From a ML perspective we rely, in most cases, on an L-BFGS solver initialized with SGD (see, eg, A. Agarwal et al. A Reliable Effective Terascale Linear Learning System). 26
  • 27. Copyright © 2015 Criteo Distribution of L-BFGS & SGD • L-BFGS, being a batch algorithm, is easy to distribute. • SGD is a bit tricker: we do parameter averaging for that and we also use Hogwild! to multi-thread on each machine. • We use Hadoop AllReduce: 27
  • 28. Copyright © 2015 Criteo A word on more advanced techniques • Irma is not only about vanilla logistic regression with L2 regularization…  • It contains more advanced techniques such as, e.g., transfer learning, factorization machines, learning to rank, cost-sensitive learning, … • We for example use cost-sensitive learning for bidding. 28
  • 29. Copyright © 2015 Criteo Outline • Introduction to the AdTech / Criteo • Deep dive into our ML algorithms • Offline and online evaluation • Future areas of research 29
  • 30. Copyright © 2015 Criteo Offline & online evaluation Usual two-step process: • Offline testing is fast, cheap, and efficient for wide exploration. • Online testing is expensive but has the ultimate word. 30
  • 31. Copyright © 2015 Criteo Offline metrics (bidding case) • We use classical metrics: LLH, RMSE, … (which focus on the prediction and ignore the bidding system where we use these models). • Utility from Offline Evaluation of Response Prediction in Online Advertising Auctions by O. Chapelle (WWW’15). 31
  • 32. Copyright © 2015 Criteo Online metrics (bidding case) • RevExTac = Revenue Excluding Traffic Acquisition Costs • Cost, Revenue, … 32
  • 33. Copyright © 2015 Criteo Some statistics on evaluation • 100K+ offline tests per year • 1K+ A/B tests per year • Many people  33 • We developed a platform and processes that enable very fast testing and improvement
  • 34. Copyright © 2015 Criteo Outline • Introduction to the AdTech / Criteo • Deep dive into our ML algorithms • Offline and online evaluation • Future areas of research 34
  • 35. Copyright © 2015 Criteo Some examples of future areas of Research • Counterfactual evaluation (offline A/B tests) • Embeddings for recommandation • Policy learning 35
  • 36. Copyright © 2015 Criteo Counterfactual evaluation • Estimate the business metric directly (clicks, sales, …). • Using the production model + randomization. • Good results on clicks already. 36
  • 37. Copyright © 2015 Criteo Embeddings for recommandation • Can embeddings (for example a la word2vec) help us compute similarities between, e.g., different products or users? 37
  • 38. Copyright © 2015 Criteo Policy learning – example on Look & Feel optimization • Classical supervised machine learning approach: learn a pClick model and sort by predicted values for each possible value (e.g, each color). • This is a hard problem and may be overkill! • Really, we only want to know which color is the best according to some business metric (eg, sales). 38
  • 39. Copyright © 2015 Criteo Academic research @ Criteo • Our 1st public dataset is online: http://bit.ly/1vgw2XC • New 1TB dataset released last year. • Some recent publications: Offline Evaluation of Response Prediction in Online Advertising Auctions. O. Chapelle, WWW’15. Sources of Variability in Large-scale Machine Learning Systems. D. Lefortier, A. Truchet, and M. de Rijke, NIPS 2015, workshop on ML systems, 2015. Cost-sensitive Learning for Bidding in Online Advertising Auctions. F. Vasile and D. Lefortier, NIPS workshop on ML for e-Commerce, 2015. 39
  • 40. Copyright © 2015 Criteo Questions d.lefortier@criteo.com