Submit Search
Upload
RecsysFR: Criteo presentation
•
Download as PPTX, PDF
•
1 like
•
2,317 views
R
recsysfr
Follow
Talk given by Etienne Sanson, Criteo during the RecsysFR meetup on October 6th 2016.
Read less
Read more
Internet
Report
Share
Report
Share
1 of 13
Download now
Recommended
Pulpix - Video Recommendation at Scale
Pulpix - Video Recommendation at Scale
recsysfr
New machine learning challenges at Criteo
New machine learning challenges at Criteo
Olivier Koch
Machine learning at Criteo - Paris Datageeks
Machine learning at Criteo - Paris Datageeks
Nicolas Le Roux
New challenges for scalable machine learning in online advertising
New challenges for scalable machine learning in online advertising
Olivier Koch
EN - Criteo - BD Deck -July 2014 - rebrand
EN - Criteo - BD Deck -July 2014 - rebrand
Djilali Zitouni
[Correction 250+ Attendees] Event Report - ADP ReThink 2019 - Global Success,...
[Correction 250+ Attendees] Event Report - ADP ReThink 2019 - Global Success,...
Holger Mueller
Ingrid IHASZ: Hungarian digital & programmatic advertising market overview / ...
Ingrid IHASZ: Hungarian digital & programmatic advertising market overview / ...
Ingrid Ihasz
Cwin16 tls-s daniel-georice
Cwin16 tls-s daniel-georice
Capgemini
Recommended
Pulpix - Video Recommendation at Scale
Pulpix - Video Recommendation at Scale
recsysfr
New machine learning challenges at Criteo
New machine learning challenges at Criteo
Olivier Koch
Machine learning at Criteo - Paris Datageeks
Machine learning at Criteo - Paris Datageeks
Nicolas Le Roux
New challenges for scalable machine learning in online advertising
New challenges for scalable machine learning in online advertising
Olivier Koch
EN - Criteo - BD Deck -July 2014 - rebrand
EN - Criteo - BD Deck -July 2014 - rebrand
Djilali Zitouni
[Correction 250+ Attendees] Event Report - ADP ReThink 2019 - Global Success,...
[Correction 250+ Attendees] Event Report - ADP ReThink 2019 - Global Success,...
Holger Mueller
Ingrid IHASZ: Hungarian digital & programmatic advertising market overview / ...
Ingrid IHASZ: Hungarian digital & programmatic advertising market overview / ...
Ingrid Ihasz
Cwin16 tls-s daniel-georice
Cwin16 tls-s daniel-georice
Capgemini
Injecting semantic links into a graph-based recommender system
Injecting semantic links into a graph-based recommender system
recsysfr
What can bring library metadata to the web? Trust, links and love
What can bring library metadata to the web? Trust, links and love
recsysfr
Dictionary Learning for Massive Matrix Factorization
Dictionary Learning for Massive Matrix Factorization
recsysfr
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
recsysfr
Recommendation @ Meetic
Recommendation @ Meetic
recsysfr
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
recsysfr
Sequential Learning in the Position-Based Model
Sequential Learning in the Position-Based Model
recsysfr
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
recsysfr
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
recsysfr
Selling Display to Your SMB Clients
Selling Display to Your SMB Clients
Acquisio
Selling display display to your smb clients final
Selling display display to your smb clients final
Acquisio
Thomvest Advertising Technology overview - Sept 2014
Thomvest Advertising Technology overview - Sept 2014
andrewtweed1
Tag Management : A Key Component of an International Digital Strategy
Tag Management : A Key Component of an International Digital Strategy
Ensighten
Oct-2016_AdAsia Credentials
Oct-2016_AdAsia Credentials
Dang Pham
Machine Learning for Computational Advertising
Machine Learning for Computational Advertising
Paris Women in Machine Learning and Data Science
EBU (Geneva, April 2016)
EBU (Geneva, April 2016)
Nice People At Work
Big Data at Tube: Events to Insights to Action
Big Data at Tube: Events to Insights to Action
Murtaza Doctor
From Analytics to Intelligence
From Analytics to Intelligence
Catherine Mylinh
SCREENlens - People Tracking with Quividi
SCREENlens - People Tracking with Quividi
pilot Screentime GmbH
The Importance of a Data-Driven Dynamic Creative Strategy
The Importance of a Data-Driven Dynamic Creative Strategy
In Marketing We Trust
Smaato - NOAH16 Berlin
Smaato - NOAH16 Berlin
NOAH Advisors
S4M - NOAH15 London
S4M - NOAH15 London
NOAH Advisors
More Related Content
Viewers also liked
Injecting semantic links into a graph-based recommender system
Injecting semantic links into a graph-based recommender system
recsysfr
What can bring library metadata to the web? Trust, links and love
What can bring library metadata to the web? Trust, links and love
recsysfr
Dictionary Learning for Massive Matrix Factorization
Dictionary Learning for Massive Matrix Factorization
recsysfr
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
recsysfr
Recommendation @ Meetic
Recommendation @ Meetic
recsysfr
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
recsysfr
Sequential Learning in the Position-Based Model
Sequential Learning in the Position-Based Model
recsysfr
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
recsysfr
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
recsysfr
Viewers also liked
(9)
Injecting semantic links into a graph-based recommender system
Injecting semantic links into a graph-based recommender system
What can bring library metadata to the web? Trust, links and love
What can bring library metadata to the web? Trust, links and love
Dictionary Learning for Massive Matrix Factorization
Dictionary Learning for Massive Matrix Factorization
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Predictive quality metrics @ tinyclues - Artem Kozhevnikov - Tinyclues
Recommendation @ Meetic
Recommendation @ Meetic
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
Meta-Prod2Vec: Simple Product Embeddings with Side-Information
Sequential Learning in the Position-Based Model
Sequential Learning in the Position-Based Model
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
CONTENT2VEC: a Joint Architecture to use Product Image and Text for the task ...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Highlights on most interesting RecSys papers - Elena Smirnova, Lowik Chanusso...
Similar to RecsysFR: Criteo presentation
Selling Display to Your SMB Clients
Selling Display to Your SMB Clients
Acquisio
Selling display display to your smb clients final
Selling display display to your smb clients final
Acquisio
Thomvest Advertising Technology overview - Sept 2014
Thomvest Advertising Technology overview - Sept 2014
andrewtweed1
Tag Management : A Key Component of an International Digital Strategy
Tag Management : A Key Component of an International Digital Strategy
Ensighten
Oct-2016_AdAsia Credentials
Oct-2016_AdAsia Credentials
Dang Pham
Machine Learning for Computational Advertising
Machine Learning for Computational Advertising
Paris Women in Machine Learning and Data Science
EBU (Geneva, April 2016)
EBU (Geneva, April 2016)
Nice People At Work
Big Data at Tube: Events to Insights to Action
Big Data at Tube: Events to Insights to Action
Murtaza Doctor
From Analytics to Intelligence
From Analytics to Intelligence
Catherine Mylinh
SCREENlens - People Tracking with Quividi
SCREENlens - People Tracking with Quividi
pilot Screentime GmbH
The Importance of a Data-Driven Dynamic Creative Strategy
The Importance of a Data-Driven Dynamic Creative Strategy
In Marketing We Trust
Smaato - NOAH16 Berlin
Smaato - NOAH16 Berlin
NOAH Advisors
S4M - NOAH15 London
S4M - NOAH15 London
NOAH Advisors
Media Management Workshop by OpenText and Skillz Middle East
Media Management Workshop by OpenText and Skillz Middle East
Dieter Hovorka
Zinnov Zones - Media & Technology 2016
Zinnov Zones - Media & Technology 2016
Zinnov
Odoo Strategy and Roadmap
Odoo Strategy and Roadmap
Odoo
Keynotes Odoo - 2014 Opendays by Fabien (CEO @ Odoo)
Keynotes Odoo - 2014 Opendays by Fabien (CEO @ Odoo)
Mustufa Rangwala
The Very Best Intranets & Digital Workplace from the 2016 Intranet Global Forum
The Very Best Intranets & Digital Workplace from the 2016 Intranet Global Forum
Prescient Digital Media
If you are not paying for it, you are the product: How much do advertisers p...
If you are not paying for it, you are the product: How much do advertisers p...
Panagiotis Papadopoulos
Accenture presentation sydney
Accenture presentation sydney
Michael Buckley
Similar to RecsysFR: Criteo presentation
(20)
Selling Display to Your SMB Clients
Selling Display to Your SMB Clients
Selling display display to your smb clients final
Selling display display to your smb clients final
Thomvest Advertising Technology overview - Sept 2014
Thomvest Advertising Technology overview - Sept 2014
Tag Management : A Key Component of an International Digital Strategy
Tag Management : A Key Component of an International Digital Strategy
Oct-2016_AdAsia Credentials
Oct-2016_AdAsia Credentials
Machine Learning for Computational Advertising
Machine Learning for Computational Advertising
EBU (Geneva, April 2016)
EBU (Geneva, April 2016)
Big Data at Tube: Events to Insights to Action
Big Data at Tube: Events to Insights to Action
From Analytics to Intelligence
From Analytics to Intelligence
SCREENlens - People Tracking with Quividi
SCREENlens - People Tracking with Quividi
The Importance of a Data-Driven Dynamic Creative Strategy
The Importance of a Data-Driven Dynamic Creative Strategy
Smaato - NOAH16 Berlin
Smaato - NOAH16 Berlin
S4M - NOAH15 London
S4M - NOAH15 London
Media Management Workshop by OpenText and Skillz Middle East
Media Management Workshop by OpenText and Skillz Middle East
Zinnov Zones - Media & Technology 2016
Zinnov Zones - Media & Technology 2016
Odoo Strategy and Roadmap
Odoo Strategy and Roadmap
Keynotes Odoo - 2014 Opendays by Fabien (CEO @ Odoo)
Keynotes Odoo - 2014 Opendays by Fabien (CEO @ Odoo)
The Very Best Intranets & Digital Workplace from the 2016 Intranet Global Forum
The Very Best Intranets & Digital Workplace from the 2016 Intranet Global Forum
If you are not paying for it, you are the product: How much do advertisers p...
If you are not paying for it, you are the product: How much do advertisers p...
Accenture presentation sydney
Accenture presentation sydney
More from recsysfr
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Five
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Five
recsysfr
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
recsysfr
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
recsysfr
Recommendations @ Rakuten Group
Recommendations @ Rakuten Group
recsysfr
Data-Driven Recommender Systems
Data-Driven Recommender Systems
recsysfr
Recommender systems
Recommender systems
recsysfr
Recommendation @Deezer
Recommendation @Deezer
recsysfr
Flexible recommender systems based on graphs
Flexible recommender systems based on graphs
recsysfr
Using Neural Networks to predict user ratings
Using Neural Networks to predict user ratings
recsysfr
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
recsysfr
Recommendation @ PriceMinister-Rakuten - Road to personalization
Recommendation @ PriceMinister-Rakuten - Road to personalization
recsysfr
Rakuten Institute of Technology Paris
Rakuten Institute of Technology Paris
recsysfr
Tailor-made personalization and recommendation - Sailendra
Tailor-made personalization and recommendation - Sailendra
recsysfr
New tools from the bandit literature to improve A/B Testing
New tools from the bandit literature to improve A/B Testing
recsysfr
Story of the algorithms behind Deezer Flow
Story of the algorithms behind Deezer Flow
recsysfr
More from recsysfr
(15)
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Five
Multi Task DPP for Basket Completion by Romain WARLOP, Fifty Five
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
Building a recommender system with Annoy and Word2Vec by Cristian PEREZ, Kern...
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
An Homophily-based Approach for Fast Post Recommendation in Microblogging Sys...
Recommendations @ Rakuten Group
Recommendations @ Rakuten Group
Data-Driven Recommender Systems
Data-Driven Recommender Systems
Recommender systems
Recommender systems
Recommendation @Deezer
Recommendation @Deezer
Flexible recommender systems based on graphs
Flexible recommender systems based on graphs
Using Neural Networks to predict user ratings
Using Neural Networks to predict user ratings
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
Preference Elicitation in Mangaki: Is Your Taste Kinda Weird?
Recommendation @ PriceMinister-Rakuten - Road to personalization
Recommendation @ PriceMinister-Rakuten - Road to personalization
Rakuten Institute of Technology Paris
Rakuten Institute of Technology Paris
Tailor-made personalization and recommendation - Sailendra
Tailor-made personalization and recommendation - Sailendra
New tools from the bandit literature to improve A/B Testing
New tools from the bandit literature to improve A/B Testing
Story of the algorithms behind Deezer Flow
Story of the algorithms behind Deezer Flow
Recently uploaded
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
JOHNBEBONYAP1
Microsoft Azure Arc Customer Deck Microsoft
Microsoft Azure Arc Customer Deck Microsoft
AanSulistiyo
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Seo
Trump Diapers Over Dems t shirts Sweatshirt
Trump Diapers Over Dems t shirts Sweatshirt
rahman018755
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Delhi Call girls
Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...
Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...
SUHANI PANDEY
20240510 QFM016 Irresponsible AI Reading List April 2024.pdf
20240510 QFM016 Irresponsible AI Reading List April 2024.pdf
Matthew Sinclair
Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...
Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...
roncy bisnoi
Katraj ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For S...
Katraj ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For S...
tanu pandey
Sarola * Female Escorts Service in Pune | 8005736733 Independent Escorts & Da...
Sarola * Female Escorts Service in Pune | 8005736733 Independent Escorts & Da...
SUHANI PANDEY
Thalassery Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call G...
Thalassery Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call G...
Call Girls In Delhi Whatsup 9873940964 Enjoy Unlimited Pleasure
VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting High Prof...
VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting High Prof...
singhpriety023
➥🔝 7737669865 🔝▻ mehsana Call-girls in Women Seeking Men 🔝mehsana🔝 Escorts...
➥🔝 7737669865 🔝▻ mehsana Call-girls in Women Seeking Men 🔝mehsana🔝 Escorts...
nirzagarg
valsad Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call Girls...
valsad Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call Girls...
Call Girls In Delhi Whatsup 9873940964 Enjoy Unlimited Pleasure
Wadgaon Sheri $ Call Girls Pune 10k @ I'm VIP Independent Escorts Girls 80057...
Wadgaon Sheri $ Call Girls Pune 10k @ I'm VIP Independent Escorts Girls 80057...
SUHANI PANDEY
Russian Call Girls Pune (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...
Russian Call Girls Pune (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...
SUHANI PANDEY
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
Nanded City ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready ...
Nanded City ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready ...
tanu pandey
VIP Call Girls Himatnagar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Himatnagar 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
kajalverma014
Recently uploaded
(20)
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
Microsoft Azure Arc Customer Deck Microsoft
Microsoft Azure Arc Customer Deck Microsoft
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Trump Diapers Over Dems t shirts Sweatshirt
Trump Diapers Over Dems t shirts Sweatshirt
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Hire↠Young Call Girls in Tilak nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esc...
Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...
Wagholi & High Class Call Girls Pune Neha 8005736733 | 100% Gennuine High Cla...
20240510 QFM016 Irresponsible AI Reading List April 2024.pdf
20240510 QFM016 Irresponsible AI Reading List April 2024.pdf
Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...
Call Girls Sangvi Call Me 7737669865 Budget Friendly No Advance BookingCall G...
Katraj ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For S...
Katraj ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For S...
Sarola * Female Escorts Service in Pune | 8005736733 Independent Escorts & Da...
Sarola * Female Escorts Service in Pune | 8005736733 Independent Escorts & Da...
Thalassery Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call G...
Thalassery Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call G...
VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting High Prof...
VIP Model Call Girls Hadapsar ( Pune ) Call ON 9905417584 Starting High Prof...
➥🔝 7737669865 🔝▻ mehsana Call-girls in Women Seeking Men 🔝mehsana🔝 Escorts...
➥🔝 7737669865 🔝▻ mehsana Call-girls in Women Seeking Men 🔝mehsana🔝 Escorts...
valsad Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call Girls...
valsad Escorts Service ☎️ 6378878445 ( Sakshi Sinha ) High Profile Call Girls...
Wadgaon Sheri $ Call Girls Pune 10k @ I'm VIP Independent Escorts Girls 80057...
Wadgaon Sheri $ Call Girls Pune 10k @ I'm VIP Independent Escorts Girls 80057...
Russian Call Girls Pune (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...
Russian Call Girls Pune (Adult Only) 8005736733 Escort Service 24x7 Cash Pay...
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Pollachi 7001035870 Whatsapp Number, 24/07 Booking
Nanded City ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready ...
Nanded City ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready ...
VIP Call Girls Himatnagar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Himatnagar 7001035870 Whatsapp Number, 24/07 Booking
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
RecsysFR: Criteo presentation
1.
RecSys FR: 4th
Session 6th October 2016 Etienne Sanson – manager R&D Engine
2.
About Criteo 1
3.
3 | Copyright
© 2016 Criteo Our mission TARGET THE RIGHT USER AT THE RIGHT TIME WITH THE RIGHT MESSAGE
4.
4 | Copyright
© 2016 Criteo Key Figures 16 000 PUBLISHERS 90% RETENTION RATE2 +130 COUNTRIES LISTED ON THE NASDAQ SINCE OCTOBER 2013 R&D REPRESENTS 21% OF THE WORKFORCE 2000 EMPLOYEES 21 BILLIONS $3 11 000 ADVERTISERS 1.19 bn€1 31 OFFICES 1: REVENUE IN 2015 2: ANNUAL RATE 2015 3: $ OF TURNOVER GENERATED TO OUR CLIENTS - TURNOVER POST-CLICK WW FROM JANUARY TO DECEMBER 2015
5.
5 | Copyright
© 2016 Criteo Revenue Growth 2009 2010 2011 2012 2013 22M$ 86M$ 199M$ 349M$ 589M$ 988M$ 2014 1,3MM$ 2015
6.
6 | Copyright
© 2016 Criteo GENERAL CONCEPT Users visit an advertiser’s website 1 Criteo identifies the users (via cookies) 2 Users leave the advertiser’s website & browse publisher on the Internet 3 Criteo identifies users on these pages (via cookie) 4 Criteo displays an advertising banner, personalized for each user 5 Click through directly to the advertiser’s page 6 @ Retargeting principles
7.
7 | Copyright
© 2016 Criteo Infrastructure Key Figures Sunnyvale 2 PoP 500 kVA 1 559 Servers New York 2 PoP 930 kVA 2 625 Servers Hong Kong 2 PoP 472 kVA 2185 Servers Paris 4 Pop 1 800 kVA 3 625 Servers Amsterdam 2 PoP +2 500 kVA 3 609 Servers Tokyo 2 PoP 455 kVA 2 564 Servers Shanghai 1 PoP 200 kVA 931 Servers World Wide 15 PoP 6,8 MVA 17 098 Servers > 55Gbps + 2.5M req/s Hosting Global Partners :
8.
About ML@Criteo 2
9.
9 | Copyright
© 2016 Criteo Our challenges – Product recommendation • Select the best ~10 products to show to a user • >1B users • Product catalog contains ~1M items, up to 1B • Time constraints: 20ms • Combination of offline/online processing steps • CF • Product embeddings (word2vec -> prod2vec) • CNN for image features What products should we recommend?
10.
10 | Copyright
© 2016 Criteo Our challenges - Bidding How much should we bid for this display? What is the best campaign to display? My company BUY! BUY! BUY! BUY! • Select the best campaign to display and evaluate its value in a few ms • Large scale regression models • >1B daily displays (but few positive examples!) • >1M parameters • Distributed optimization (SGD, L-BFGS) • Feature Engineering • Transfer learning, FFM, Policy learning • Marketplace, game theory, auction theory
11.
11 | Copyright
© 2016 Criteo Our challenges – X-device • Build a huge graph (Billions of nodes/edges): • Nodes = devices • Edge = the 2 devices belong to the same user • How to connect 2 devices? • How to know the ground truth? • How to keep it stable? • At scale & taking care about privacy Who is the user behind the device?
12.
12 | Copyright
© 2016 Criteo Our challenges – Testing • We test everything! • Offline tests / AB Tests • Infrastructure to perform large-scale tests • >100K offline tests / year • >1K AB Tests / year • Dedicated teams • Technical / Business Metrics • Randomization • Counterfactual evaluation
13.
Thank you! …and we’re
hiring!
Editor's Notes
How to connect? We have some data that allows for deterministic match, but we also have to build a probabilistic match
Hashing trick, one-hot encoding, distributed optimization Tradeoff between freshness of model and historical data Irma
How to connect? We have some data that allows for deterministic match, but we also have to build a probabilistic match
trade-off fast-cheap / expensive-truth
Download now