SlideShare uma empresa Scribd logo
1 de 13
WHAT DOES IT TAKE TO WIN THE
KAGGLE/YANDEX COMPETITION

Christophe Bourguignat
Kenji Lefèvre-Hasegawa
Paul Masurel @Dataiku
Matthieu Scordia @Dataiku
OUTLINE OF THE TALK

• Review of the Kaggle/Yandex Challenge
• How we worked (team work & tools)
• The winning model
GOAL Re-rank URLs returned by Yandex according to
the personal preferences of the users
url1

url3

url2

url2
GOAL

url3

url1

url4

url4

ML CHALLENGE Predict user’s pertinence

for urls and rerank result set accordingly
The Kaggle/Yandex challenge
GIVEN
• 30 days logs test: 3 days, train: 27 days
• Users historic queries, clicks & dwell-times
Q

Q

Q

Q

• Test session prior activity queries, clicks & dwell-times
Test session :

SIZE
• 15Gb size
The Kaggle/Yandex challenge

Q

Q

T

?
QUALITY METRIC
• One query test / user on the last 3 days
• NDCG metric penalize error of pertinence on top ranked
urls

• No A/B test
url1
url2

OK

BAD

url4
url3

Kaggle
The Kaggle/Yandex challenge

Prediction

Another ranking
TEAM DATAIKU SCIENCE STUDIO / KAGGLE

•
•
•
•

Christophe Bourguignat Engineer, Data enthusiastic
Kenji Lefèvre-Hasegawa Ph.D. math, new to ML
Paul Masurel Software Engineer @dataiku
Matthieu Scordia Data Scientist @dataiku
First meeting : October16th 2013

How we worked (Team work & tools)
WE’VE USED
•
•
•
•
•

Related papers (mainly Microsoft’s)
12 core, 64 Gb
Python scikit-learn
Dataiku Science Studio
Java Ranklib

How we worked (Team work & tools)
DATAIKU SCIENCE STUDIO
Features & labels

Features

Labels

Split train & validation

Original train

LEARNING
Team members
work independantly

FEATURES CONSTRUCTION
Team members work
independantly
DATA DRIVEN
COMPUTATION
How we worked (Team work & tools)
HOW MUCH WORK ?
• 960+ emails
• 360+ features
• 50+ ideas grid tuned (300+ models fitted)
• Server heavily loaded the last 3 weeks
• 56 kaggle submissions
• 196 teams, 264 players, 3570 submissions

How we worked (Team work & tools)

2014-01-01

1st

Future top 2 & 3
enter race

1 week

3rd

1 week

1st

5th

Top 10

Top 25

1/2 month

1 week
PROBLEM ANALYSIS
Query

Result Set
• Rank
• URL Snippet Quality
• URL is skipped, clicked or missed

CLICK
Reading URL
• URL & Domain pertinence with dwell-time

The winning model
FEATURES
Features :
• Rank
• User habits, query specificity (entropy, frequency,…)
• Snippet pertinence
• Missed, Skipped, Clicked
• URL & Domain Pertinence
Declinaison of
& Clicked
• Probability, Stimuli freq., Mean Reciprocal Rank (MRR)
• For each user : historic & previous activity in test session &
aggregate
• For all user
• Declined for all queries & same query
The winning model
MODELS
• Random Forest (predict proba)
+ maximize E(NDCG)
Kaggle/Yandex Top 1
then 3rd

• Lambda MART (Gradient Boosting Tree
optimized for NDCG) WINS !
The winning model
QUESTIONS

?
Thank you !

Mais conteúdo relacionado

Semelhante a What does it take to win the Kaggle/Yandex competition

Agile testing experiments
Agile testing experimentsAgile testing experiments
Agile testing experiments
Baiju Joseph
 
20121213 qa introduction smileryang
20121213 qa introduction smileryang20121213 qa introduction smileryang
20121213 qa introduction smileryang
netdbncku
 
User centered agile dev balanced team 2013
User centered agile dev balanced team 2013User centered agile dev balanced team 2013
User centered agile dev balanced team 2013
Jay Trimble
 
Journey of Migrating Millions of Queries on The Cloud
Journey of Migrating Millions of Queries on The CloudJourney of Migrating Millions of Queries on The Cloud
Journey of Migrating Millions of Queries on The Cloud
takezoe
 
SCQAA-SF Meeting on May 21 2014
SCQAA-SF Meeting on May 21 2014 SCQAA-SF Meeting on May 21 2014
SCQAA-SF Meeting on May 21 2014
Sujit Ghosh
 

Semelhante a What does it take to win the Kaggle/Yandex competition (20)

Emptying Your Cup an Agile Primer
Emptying Your Cup an Agile Primer Emptying Your Cup an Agile Primer
Emptying Your Cup an Agile Primer
 
Agile testing experiments
Agile testing experimentsAgile testing experiments
Agile testing experiments
 
SenchaCon 2016: Creating a Flexible and Usable Industry Specific Solution - D...
SenchaCon 2016: Creating a Flexible and Usable Industry Specific Solution - D...SenchaCon 2016: Creating a Flexible and Usable Industry Specific Solution - D...
SenchaCon 2016: Creating a Flexible and Usable Industry Specific Solution - D...
 
Continuous Delivery without Significant Test Automation
Continuous Delivery without Significant Test AutomationContinuous Delivery without Significant Test Automation
Continuous Delivery without Significant Test Automation
 
My Experiments In Agile Testing in Yahoo.pptx
My Experiments In Agile Testing in Yahoo.pptxMy Experiments In Agile Testing in Yahoo.pptx
My Experiments In Agile Testing in Yahoo.pptx
 
Play with Kaggle
Play with KagglePlay with Kaggle
Play with Kaggle
 
Moving from fast to solr on atg
Moving from fast to solr on atgMoving from fast to solr on atg
Moving from fast to solr on atg
 
CommerceSearch: Moving from FAST to Solr on ATG
CommerceSearch: Moving from FAST to Solr on ATGCommerceSearch: Moving from FAST to Solr on ATG
CommerceSearch: Moving from FAST to Solr on ATG
 
Agile Testing
Agile TestingAgile Testing
Agile Testing
 
20121213 qa introduction smileryang
20121213 qa introduction smileryang20121213 qa introduction smileryang
20121213 qa introduction smileryang
 
User Centered Agile Development at NASA - One Groups Path to Better Software
User Centered Agile Development at NASA - One Groups Path to Better SoftwareUser Centered Agile Development at NASA - One Groups Path to Better Software
User Centered Agile Development at NASA - One Groups Path to Better Software
 
User centered agile dev balanced team 2013
User centered agile dev balanced team 2013User centered agile dev balanced team 2013
User centered agile dev balanced team 2013
 
Agile by KD
Agile by KDAgile by KD
Agile by KD
 
Agile by KD
Agile by KDAgile by KD
Agile by KD
 
Journey of Migrating Millions of Queries on The Cloud
Journey of Migrating Millions of Queries on The CloudJourney of Migrating Millions of Queries on The Cloud
Journey of Migrating Millions of Queries on The Cloud
 
SCQAA-SF Meeting on May 21 2014
SCQAA-SF Meeting on May 21 2014 SCQAA-SF Meeting on May 21 2014
SCQAA-SF Meeting on May 21 2014
 
Resume
ResumeResume
Resume
 
Scalability and performance for e commerce
Scalability and performance for e commerceScalability and performance for e commerce
Scalability and performance for e commerce
 
Effective Scrum
Effective ScrumEffective Scrum
Effective Scrum
 
Java Certification by HUJAK - 2015-05-12 - at JavaCro'15 conference
Java Certification by HUJAK - 2015-05-12 - at JavaCro'15 conferenceJava Certification by HUJAK - 2015-05-12 - at JavaCro'15 conference
Java Certification by HUJAK - 2015-05-12 - at JavaCro'15 conference
 

Último

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
giselly40
 

Último (20)

Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
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
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
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
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
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
 
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
 
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
 
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
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 

What does it take to win the Kaggle/Yandex competition

  • 1. WHAT DOES IT TAKE TO WIN THE KAGGLE/YANDEX COMPETITION Christophe Bourguignat Kenji Lefèvre-Hasegawa Paul Masurel @Dataiku Matthieu Scordia @Dataiku
  • 2. OUTLINE OF THE TALK • Review of the Kaggle/Yandex Challenge • How we worked (team work & tools) • The winning model
  • 3. GOAL Re-rank URLs returned by Yandex according to the personal preferences of the users url1 url3 url2 url2 GOAL url3 url1 url4 url4 ML CHALLENGE Predict user’s pertinence for urls and rerank result set accordingly The Kaggle/Yandex challenge
  • 4. GIVEN • 30 days logs test: 3 days, train: 27 days • Users historic queries, clicks & dwell-times Q Q Q Q • Test session prior activity queries, clicks & dwell-times Test session : SIZE • 15Gb size The Kaggle/Yandex challenge Q Q T ?
  • 5. QUALITY METRIC • One query test / user on the last 3 days • NDCG metric penalize error of pertinence on top ranked urls • No A/B test url1 url2 OK BAD url4 url3 Kaggle The Kaggle/Yandex challenge Prediction Another ranking
  • 6. TEAM DATAIKU SCIENCE STUDIO / KAGGLE • • • • Christophe Bourguignat Engineer, Data enthusiastic Kenji Lefèvre-Hasegawa Ph.D. math, new to ML Paul Masurel Software Engineer @dataiku Matthieu Scordia Data Scientist @dataiku First meeting : October16th 2013 How we worked (Team work & tools)
  • 7. WE’VE USED • • • • • Related papers (mainly Microsoft’s) 12 core, 64 Gb Python scikit-learn Dataiku Science Studio Java Ranklib How we worked (Team work & tools)
  • 8. DATAIKU SCIENCE STUDIO Features & labels Features Labels Split train & validation Original train LEARNING Team members work independantly FEATURES CONSTRUCTION Team members work independantly DATA DRIVEN COMPUTATION How we worked (Team work & tools)
  • 9. HOW MUCH WORK ? • 960+ emails • 360+ features • 50+ ideas grid tuned (300+ models fitted) • Server heavily loaded the last 3 weeks • 56 kaggle submissions • 196 teams, 264 players, 3570 submissions How we worked (Team work & tools) 2014-01-01 1st Future top 2 & 3 enter race 1 week 3rd 1 week 1st 5th Top 10 Top 25 1/2 month 1 week
  • 10. PROBLEM ANALYSIS Query Result Set • Rank • URL Snippet Quality • URL is skipped, clicked or missed CLICK Reading URL • URL & Domain pertinence with dwell-time The winning model
  • 11. FEATURES Features : • Rank • User habits, query specificity (entropy, frequency,…) • Snippet pertinence • Missed, Skipped, Clicked • URL & Domain Pertinence Declinaison of & Clicked • Probability, Stimuli freq., Mean Reciprocal Rank (MRR) • For each user : historic & previous activity in test session & aggregate • For all user • Declined for all queries & same query The winning model
  • 12. MODELS • Random Forest (predict proba) + maximize E(NDCG) Kaggle/Yandex Top 1 then 3rd • Lambda MART (Gradient Boosting Tree optimized for NDCG) WINS ! The winning model