SlideShare uma empresa Scribd logo
1 de 33
Baixar para ler offline
Nir Yungster
Kamil Sindi
● Open source video player + video
platform
● 5% of all video plays on the web
● Per month:
○ 40Bn plays
○ 100 TB events
● 15K Customers
PLAYER Data
Analytics
The fastest online
video player
(2008)
Data-driven products (e.g.
Recommendations)
(2016)
Dashboards, Audience
Measurement
(2014)
Video Management
and Delivery
(2011)
PLATFORM
Increases views, engagement and ad revenue with minimal effort or
investment by publisher
JW Recommendations
● 20K requests per second
● Support legacy endpoints
○ Non-recommendations playlists
● Business rule features (e.g. sunrise, sunset, geo block)
● Include video metadata in response (conversions, manifest, etc.)
● Pass product “sniff test”
● Rudimentary A/B testing using click-through rates
○ Beat random
Association-based
recommendations
Content-based
recommendations
(& Trending videos)
Title: Top ten Snowboarding
Destinations in Colorado
Description, keywords
● Association → Association Rule Mining
○ Viewers who watched X also watched Y
● Content → BM25 (think tf-idf)
○ Elasticsearch
● Trending
○ Exp. weighted moving avg of plays
Rec 1: “Best hotels in Boulder”
Rec 2: “Amazing 1080”
Rec 3: “Best ski slopes in Colorado”
Rec 4: “Snowboarding is fun!”
Rec 5: “Top Snowboarding schools”
Rec 6: “Kardashian Katastrophe!”
Rec 7: “Cats on Skis”
Top ten Snowboarding
Destinations in Colorado, 2018
Similar titles
Highly
co-watched
Trending
Association Pipeline Content Pipeline
✓ 20K requests per second
✓ Support legacy endpoints
✓ Business rule features (e.g. sunset, sunrise, geo block)
✓ Include video metadata in response (conversions, manifest, etc.)
○ Use log-based architecture to sync from various sources
✓ Pass product “sniff test”
✓ Rudimentary A/B testing
○ Beat random when looking at Overlay Click-Through Rate
○ Bested competitors in customer-led A/B tests
How can we drive more value to customers?
How can we continue to grow competitive advantage?
Click Through Rate Completion Rate
Ad Impressions Viewer Time
Americans spend 2+ hrs on social media
Our publishers are fighting for time
Recommendations can drive viewer
time by either:
● More Time per Session
● More Sessions (higher retention)
● Keep viewers in consistent
variant to measure:
○ Time/session
○ Viewer retention
A/B results (JW model vs random)
● 50% more time per session on recommended content
● 10% higher viewer retention (D1, D7)
We can now run experiments and understanding
impact on viewer time
Hypothesis
“If we boost recently
produced content,
recs will be more
relevant”
Experiment
What happens to
time spent?
Experiment ResultRecommendation Algorithm (hypothesis)
Swap in Word2Vec title similarity instead of tf-idf
Boost recent content
Try trending only
Try different ordering of layers
2 Weeks
3 Weeks
1 Week
2 Weeks
Fast Iteration Cycles
Build
Signals
Training
Data
Model
Model
Output
Predict
Evaluation,
validation
Improve Features,
Model, Data
Run Experiment
Build
Recommendation Algorithm (hypothesis)
● Time spent in a session aggregates behavior over a sequence of
recommendations
○ Predicting that directly is hard
● Pick closely related metric to measure effectiveness of a single
recommendation
○ Time watched, percent watched?
○ Probability of an “engaged watch”
Video 1 Video 2
Pairwise Empirical Engagement Rate
(PEER Score)
PEER Score = Wilson Score ( )
% video 2 watches >= 30 seconds
Metric for List of Recommended Videos V :
nDCG (V), where PEER is relevance metric
● Significant improvement
to time watched
○ 10% - 40% increase
● Improved CTR too
● Algorithm performance
○ Association vs Content
○ Optimal Training Window
● Publishers with viral events that affect results
○ Test results change with such events
● Publisher quirks
○ Player, Recommendations implementation
● Algorithmic Perspective
○ More Context
○ Personalization
○ Progress in deep learning for recs
● Implementation / Maintainability
○ Single Unified Model (for widely varying publishers)
○ Flexible inputs (Anything2Vec)
● Built and A/B tested Tensorflow
model that performs on par with
our current algorithms
● Same context, unpersonalized
● AWS SageMaker used for training
on GPUs, serving model via
Tensorflow Serving
● Trained using triplet loss to learn
video embeddings
Anchor
Positive
Example
Negative
Example
FaceNet: A Unified Embedding for Face Recognition and
Clustering (2015)
● Modeling
○ Score individual videos vs. learn to rank
○ How to choose positive & negative training samples?
○ Relevance metric for hyperparameter tuning
● Architecture
○ API traffic
○ Viewer profile service
○ Tensorflow is free, but scaling it is not
● “Just build” can work great for MVP recommender
● Offline testing critical for algorithmic improvement
● Finding the right offline metric is key
Data Science
Graham Edge
Matthew Yu
Rik Heijdens
Bobby Han
Engineering
Doug Shore
Alex Halter
Linda Cai
Dan Meng
Leo Yu
Franklin Dement
Strata NYC: Building turn-key recommendations for 5% of internet video

Mais conteúdo relacionado

Semelhante a Strata NYC: Building turn-key recommendations for 5% of internet video

Scaling Growth and UA in mobile gaming based on Peaksel example
Scaling Growth and UA in mobile gaming based on Peaksel exampleScaling Growth and UA in mobile gaming based on Peaksel example
Scaling Growth and UA in mobile gaming based on Peaksel exampleGameCamp
 
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning SystemsXavier Amatriain
 
Control Your Video App's Destiny: Managing your post-launch D2C strategy
Control Your Video App's Destiny: Managing your post-launch D2C strategyControl Your Video App's Destiny: Managing your post-launch D2C strategy
Control Your Video App's Destiny: Managing your post-launch D2C strategyJoshua Shulman, MA
 
Criteo TektosData Meetup
Criteo TektosData MeetupCriteo TektosData Meetup
Criteo TektosData MeetupOlivier Koch
 
A/B Testing for WordPress & Drupal
A/B Testing for WordPress & DrupalA/B Testing for WordPress & Drupal
A/B Testing for WordPress & DrupalOptimizely
 
UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...
UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...
UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...UserZoom
 
YouTube SEO ( A guide to YouTube SEO)
YouTube SEO ( A guide to YouTube SEO)YouTube SEO ( A guide to YouTube SEO)
YouTube SEO ( A guide to YouTube SEO)Abhishek Das Roy
 
Optimal Search Engine Marketing
Optimal Search Engine MarketingOptimal Search Engine Marketing
Optimal Search Engine MarketingBernd Skiera
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender SystemsYves Raimond
 
Webinar: Acting Like a Top 25 ISV - Demo Org Optimization
Webinar: Acting Like a Top 25 ISV - Demo Org OptimizationWebinar: Acting Like a Top 25 ISV - Demo Org Optimization
Webinar: Acting Like a Top 25 ISV - Demo Org OptimizationCodeScience
 
Website testing & optimization framework & results
Website testing & optimization framework & resultsWebsite testing & optimization framework & results
Website testing & optimization framework & resultsSaad Hameed
 
Optimizely Product Vision: The Future of Experimentation
Optimizely Product Vision: The Future of ExperimentationOptimizely Product Vision: The Future of Experimentation
Optimizely Product Vision: The Future of ExperimentationOptimizely
 
Userlytics User Testing: The Basics
Userlytics User Testing: The BasicsUserlytics User Testing: The Basics
Userlytics User Testing: The BasicsUserlyitcs-Ryan
 
User testing methodology
User testing methodologyUser testing methodology
User testing methodologyJames Hatfield
 
10+ Tactics to Increase Your B2B Leads from Search Engines
10+ Tactics to Increase Your B2B Leads from Search Engines10+ Tactics to Increase Your B2B Leads from Search Engines
10+ Tactics to Increase Your B2B Leads from Search EnginesAndrew Choco
 
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...Gabriel Moreira
 
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...Gabriel Moreira
 
Pivotal Tracker - Research Findings
Pivotal Tracker - Research FindingsPivotal Tracker - Research Findings
Pivotal Tracker - Research FindingsPaulina Galindo
 
Ronny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynote
Ronny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynoteRonny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynote
Ronny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynoteOnline Dialogue
 

Semelhante a Strata NYC: Building turn-key recommendations for 5% of internet video (20)

Scaling Growth and UA in mobile gaming based on Peaksel example
Scaling Growth and UA in mobile gaming based on Peaksel exampleScaling Growth and UA in mobile gaming based on Peaksel example
Scaling Growth and UA in mobile gaming based on Peaksel example
 
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
Strata 2016 -  Lessons Learned from building real-life Machine Learning SystemsStrata 2016 -  Lessons Learned from building real-life Machine Learning Systems
Strata 2016 - Lessons Learned from building real-life Machine Learning Systems
 
Control Your Video App's Destiny: Managing your post-launch D2C strategy
Control Your Video App's Destiny: Managing your post-launch D2C strategyControl Your Video App's Destiny: Managing your post-launch D2C strategy
Control Your Video App's Destiny: Managing your post-launch D2C strategy
 
Criteo TektosData Meetup
Criteo TektosData MeetupCriteo TektosData Meetup
Criteo TektosData Meetup
 
A/B Testing for WordPress & Drupal
A/B Testing for WordPress & DrupalA/B Testing for WordPress & Drupal
A/B Testing for WordPress & Drupal
 
UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...
UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...
UserZoom Education Series - Research Deep Dive - Advanced - Task-Based TOL (b...
 
YouTube SEO ( A guide to YouTube SEO)
YouTube SEO ( A guide to YouTube SEO)YouTube SEO ( A guide to YouTube SEO)
YouTube SEO ( A guide to YouTube SEO)
 
Optimal Search Engine Marketing
Optimal Search Engine MarketingOptimal Search Engine Marketing
Optimal Search Engine Marketing
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender Systems
 
Webinar: Acting Like a Top 25 ISV - Demo Org Optimization
Webinar: Acting Like a Top 25 ISV - Demo Org OptimizationWebinar: Acting Like a Top 25 ISV - Demo Org Optimization
Webinar: Acting Like a Top 25 ISV - Demo Org Optimization
 
Website testing & optimization framework & results
Website testing & optimization framework & resultsWebsite testing & optimization framework & results
Website testing & optimization framework & results
 
Optimizely Product Vision: The Future of Experimentation
Optimizely Product Vision: The Future of ExperimentationOptimizely Product Vision: The Future of Experimentation
Optimizely Product Vision: The Future of Experimentation
 
Userlytics User Testing: The Basics
Userlytics User Testing: The BasicsUserlytics User Testing: The Basics
Userlytics User Testing: The Basics
 
User testing methodology
User testing methodologyUser testing methodology
User testing methodology
 
10+ Tactics to Increase Your B2B Leads from Search Engines
10+ Tactics to Increase Your B2B Leads from Search Engines10+ Tactics to Increase Your B2B Leads from Search Engines
10+ Tactics to Increase Your B2B Leads from Search Engines
 
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
 
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
PAPIs LATAM 2019 - Training and deploying ML models with Kubeflow and TensorF...
 
youtube.docx
youtube.docxyoutube.docx
youtube.docx
 
Pivotal Tracker - Research Findings
Pivotal Tracker - Research FindingsPivotal Tracker - Research Findings
Pivotal Tracker - Research Findings
 
Ronny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynote
Ronny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynoteRonny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynote
Ronny Kohavi, Microsoft (USA) - Conversion Hotel 2017 - keynote
 

Último

Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi EscortsIndian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi EscortsMonica Sydney
 
APNIC Updates presented by Paul Wilson at ARIN 53
APNIC Updates presented by Paul Wilson at ARIN 53APNIC Updates presented by Paul Wilson at ARIN 53
APNIC Updates presented by Paul Wilson at ARIN 53APNIC
 
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...kajalverma014
 
Microsoft Azure Arc Customer Deck Microsoft
Microsoft Azure Arc Customer Deck MicrosoftMicrosoft Azure Arc Customer Deck Microsoft
Microsoft Azure Arc Customer Deck MicrosoftAanSulistiyo
 
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac RoomVip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Roommeghakumariji156
 
Real Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirtReal Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirtrahman018755
 
20240508 QFM014 Elixir Reading List April 2024.pdf
20240508 QFM014 Elixir Reading List April 2024.pdf20240508 QFM014 Elixir Reading List April 2024.pdf
20240508 QFM014 Elixir Reading List April 2024.pdfMatthew Sinclair
 
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdfMatthew Sinclair
 
Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...gajnagarg
 
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样ayvbos
 
Best SEO Services Company in Dallas | Best SEO Agency Dallas
Best SEO Services Company in Dallas | Best SEO Agency DallasBest SEO Services Company in Dallas | Best SEO Agency Dallas
Best SEO Services Company in Dallas | Best SEO Agency DallasDigicorns Technologies
 
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查ydyuyu
 
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge GraphsEleniIlkou
 
Power point inglese - educazione civica di Nuria Iuzzolino
Power point inglese - educazione civica di Nuria IuzzolinoPower point inglese - educazione civica di Nuria Iuzzolino
Power point inglese - educazione civica di Nuria Iuzzolinonuriaiuzzolino1
 
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime NagercoilNagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoilmeghakumariji156
 
Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.krishnachandrapal52
 
"Boost Your Digital Presence: Partner with a Leading SEO Agency"
"Boost Your Digital Presence: Partner with a Leading SEO Agency""Boost Your Digital Presence: Partner with a Leading SEO Agency"
"Boost Your Digital Presence: Partner with a Leading SEO Agency"growthgrids
 
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdfpdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdfJOHNBEBONYAP1
 
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查ydyuyu
 
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查ydyuyu
 

Último (20)

Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi EscortsIndian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
Indian Escort in Abu DHabi 0508644382 Abu Dhabi Escorts
 
APNIC Updates presented by Paul Wilson at ARIN 53
APNIC Updates presented by Paul Wilson at ARIN 53APNIC Updates presented by Paul Wilson at ARIN 53
APNIC Updates presented by Paul Wilson at ARIN 53
 
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
best call girls in Hyderabad Finest Escorts Service 📞 9352988975 📞 Available ...
 
Microsoft Azure Arc Customer Deck Microsoft
Microsoft Azure Arc Customer Deck MicrosoftMicrosoft Azure Arc Customer Deck Microsoft
Microsoft Azure Arc Customer Deck Microsoft
 
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac RoomVip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
Vip Firozabad Phone 8250092165 Escorts Service At 6k To 30k Along With Ac Room
 
Real Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirtReal Men Wear Diapers T Shirts sweatshirt
Real Men Wear Diapers T Shirts sweatshirt
 
20240508 QFM014 Elixir Reading List April 2024.pdf
20240508 QFM014 Elixir Reading List April 2024.pdf20240508 QFM014 Elixir Reading List April 2024.pdf
20240508 QFM014 Elixir Reading List April 2024.pdf
 
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
20240509 QFM015 Engineering Leadership Reading List April 2024.pdf
 
Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Dindigul [ 7014168258 ] Call Me For Genuine Models ...
 
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
一比一原版(Curtin毕业证书)科廷大学毕业证原件一模一样
 
Best SEO Services Company in Dallas | Best SEO Agency Dallas
Best SEO Services Company in Dallas | Best SEO Agency DallasBest SEO Services Company in Dallas | Best SEO Agency Dallas
Best SEO Services Company in Dallas | Best SEO Agency Dallas
 
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
哪里办理美国迈阿密大学毕业证(本硕)umiami在读证明存档可查
 
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
2nd Solid Symposium: Solid Pods vs Personal Knowledge Graphs
 
Power point inglese - educazione civica di Nuria Iuzzolino
Power point inglese - educazione civica di Nuria IuzzolinoPower point inglese - educazione civica di Nuria Iuzzolino
Power point inglese - educazione civica di Nuria Iuzzolino
 
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime NagercoilNagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
Nagercoil Escorts Service Girl ^ 9332606886, WhatsApp Anytime Nagercoil
 
Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.Meaning of On page SEO & its process in detail.
Meaning of On page SEO & its process in detail.
 
"Boost Your Digital Presence: Partner with a Leading SEO Agency"
"Boost Your Digital Presence: Partner with a Leading SEO Agency""Boost Your Digital Presence: Partner with a Leading SEO Agency"
"Boost Your Digital Presence: Partner with a Leading SEO Agency"
 
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdfpdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
pdfcoffee.com_business-ethics-q3m7-pdf-free.pdf
 
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查在线制作约克大学毕业证(yu毕业证)在读证明认证可查
在线制作约克大学毕业证(yu毕业证)在读证明认证可查
 
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
原版制作美国爱荷华大学毕业证(iowa毕业证书)学位证网上存档可查
 

Strata NYC: Building turn-key recommendations for 5% of internet video

  • 2.
  • 3.
  • 4. ● Open source video player + video platform ● 5% of all video plays on the web ● Per month: ○ 40Bn plays ○ 100 TB events ● 15K Customers
  • 5. PLAYER Data Analytics The fastest online video player (2008) Data-driven products (e.g. Recommendations) (2016) Dashboards, Audience Measurement (2014) Video Management and Delivery (2011) PLATFORM
  • 6.
  • 7. Increases views, engagement and ad revenue with minimal effort or investment by publisher JW Recommendations
  • 8. ● 20K requests per second ● Support legacy endpoints ○ Non-recommendations playlists ● Business rule features (e.g. sunrise, sunset, geo block) ● Include video metadata in response (conversions, manifest, etc.) ● Pass product “sniff test” ● Rudimentary A/B testing using click-through rates ○ Beat random
  • 9. Association-based recommendations Content-based recommendations (& Trending videos) Title: Top ten Snowboarding Destinations in Colorado Description, keywords
  • 10. ● Association → Association Rule Mining ○ Viewers who watched X also watched Y ● Content → BM25 (think tf-idf) ○ Elasticsearch ● Trending ○ Exp. weighted moving avg of plays
  • 11. Rec 1: “Best hotels in Boulder” Rec 2: “Amazing 1080” Rec 3: “Best ski slopes in Colorado” Rec 4: “Snowboarding is fun!” Rec 5: “Top Snowboarding schools” Rec 6: “Kardashian Katastrophe!” Rec 7: “Cats on Skis” Top ten Snowboarding Destinations in Colorado, 2018 Similar titles Highly co-watched Trending
  • 13. ✓ 20K requests per second ✓ Support legacy endpoints ✓ Business rule features (e.g. sunset, sunrise, geo block) ✓ Include video metadata in response (conversions, manifest, etc.) ○ Use log-based architecture to sync from various sources ✓ Pass product “sniff test” ✓ Rudimentary A/B testing ○ Beat random when looking at Overlay Click-Through Rate ○ Bested competitors in customer-led A/B tests
  • 14. How can we drive more value to customers? How can we continue to grow competitive advantage?
  • 15.
  • 16. Click Through Rate Completion Rate Ad Impressions Viewer Time
  • 17. Americans spend 2+ hrs on social media Our publishers are fighting for time Recommendations can drive viewer time by either: ● More Time per Session ● More Sessions (higher retention)
  • 18. ● Keep viewers in consistent variant to measure: ○ Time/session ○ Viewer retention A/B results (JW model vs random) ● 50% more time per session on recommended content ● 10% higher viewer retention (D1, D7)
  • 19. We can now run experiments and understanding impact on viewer time Hypothesis “If we boost recently produced content, recs will be more relevant” Experiment What happens to time spent?
  • 20. Experiment ResultRecommendation Algorithm (hypothesis) Swap in Word2Vec title similarity instead of tf-idf Boost recent content Try trending only Try different ordering of layers 2 Weeks 3 Weeks 1 Week 2 Weeks
  • 21. Fast Iteration Cycles Build Signals Training Data Model Model Output Predict Evaluation, validation Improve Features, Model, Data Run Experiment Build Recommendation Algorithm (hypothesis)
  • 22. ● Time spent in a session aggregates behavior over a sequence of recommendations ○ Predicting that directly is hard ● Pick closely related metric to measure effectiveness of a single recommendation ○ Time watched, percent watched? ○ Probability of an “engaged watch”
  • 23. Video 1 Video 2 Pairwise Empirical Engagement Rate (PEER Score) PEER Score = Wilson Score ( ) % video 2 watches >= 30 seconds Metric for List of Recommended Videos V : nDCG (V), where PEER is relevance metric
  • 24. ● Significant improvement to time watched ○ 10% - 40% increase ● Improved CTR too
  • 25.
  • 26. ● Algorithm performance ○ Association vs Content ○ Optimal Training Window ● Publishers with viral events that affect results ○ Test results change with such events ● Publisher quirks ○ Player, Recommendations implementation
  • 27.
  • 28. ● Algorithmic Perspective ○ More Context ○ Personalization ○ Progress in deep learning for recs ● Implementation / Maintainability ○ Single Unified Model (for widely varying publishers) ○ Flexible inputs (Anything2Vec)
  • 29. ● Built and A/B tested Tensorflow model that performs on par with our current algorithms ● Same context, unpersonalized ● AWS SageMaker used for training on GPUs, serving model via Tensorflow Serving ● Trained using triplet loss to learn video embeddings Anchor Positive Example Negative Example FaceNet: A Unified Embedding for Face Recognition and Clustering (2015)
  • 30. ● Modeling ○ Score individual videos vs. learn to rank ○ How to choose positive & negative training samples? ○ Relevance metric for hyperparameter tuning ● Architecture ○ API traffic ○ Viewer profile service ○ Tensorflow is free, but scaling it is not
  • 31. ● “Just build” can work great for MVP recommender ● Offline testing critical for algorithmic improvement ● Finding the right offline metric is key
  • 32. Data Science Graham Edge Matthew Yu Rik Heijdens Bobby Han Engineering Doug Shore Alex Halter Linda Cai Dan Meng Leo Yu Franklin Dement