SlideShare une entreprise Scribd logo
1  sur  23
Télécharger pour lire hors ligne
Classification Labels in a Fast Moving Environment
Classification Labels in a Fast Moving
Environment
Alessandro Magnani
@WalmartLabs, Walmart Global eCommerce
California, USA
Friday 13th November, 2015
Classification Labels in a Fast Moving Environment
Classification Model Performance
Items Classifier
Editor
N sampled items true label yi
estimate ˜yi
accuracyEvaluation
◮ correctly evaluating classification models is critical and
requires labels
◮ labeling products is expensive
◮ need to correctly and optimally use labels
Classification Labels in a Fast Moving Environment
Classification Model Performance
Items Classifier
Editor
N sampled items true label yi
estimate ˜yi
accuracyEvaluation
Measure accuracy common approach:
◮ sample uniformly at random N items
◮ compute accuracy 1
N
N
i=1 ½{˜yi =yi }
Classification Labels in a Fast Moving Environment
Practical challenges
Items Classifier
Editor
N sampled items true label yi
estimate ˜yi
accuracyEvaluation
◮ items change over time
Classification Labels in a Fast Moving Environment
Practical challenges
Items Classifier
Editor
N sampled items true label yi
estimate ˜yi
accuracyEvaluation
◮ items change over time
◮ evaluation required over multiple subsets
Classification Labels in a Fast Moving Environment
Practical challenges
Items Classifier
Editor
N sampled items true label yi
estimate ˜yi
accuracyEvaluation
◮ items change over time
◮ evaluation required over multiple subsets
◮ existing labels potentially hard to reuse
Classification Labels in a Fast Moving Environment
A motivating example
compute accuracy over 1M items
1K labels budget
◮ sample 1K items and get
labels yi
◮ measure accuracy
1
1K
1K
i=1 ½{˜yi =yi }
1M
p
1
1K
Classification Labels in a Fast Moving Environment
A motivating example
500K items added, compute accuracy on all 1.5M items
◮ use previous accuracy
measure
◮ most likely inaccurate
1M 1.5M
p
1
1K
Classification Labels in a Fast Moving Environment
A motivating example
500K items added, compute accuracy on all 1.5M items
500 labels extra budget
◮ sample 500 items from the
1.5M
◮ compute accuracy on new
500 labels
◮ previous 1K labels “wasted”
1M 1.5M
p
1
3K
Classification Labels in a Fast Moving Environment
A motivating example
500K items added, compute accuracy on all 1.5M items
500 labels extra budget, better approach
◮ sample 500 items from new
items
◮ compute accuracy on all 1.5K
labels
◮ no label “wasted”
1M 1.5M
p
1
1K
Classification Labels in a Fast Moving Environment
A motivating example
500K items added, compute accuracy on all 1.5M items
only 250 labels extra budget?
◮ sample 250 items from new
items
◮ need to account for difference
in sampling
◮ accuracy:
1M 1.5M
p
1
2K
1
1.5K
1K
i=1 ½{˜yi =yi } + 2 250
i=1 ½{˜ynew
i =ynew
i }
Classification Labels in a Fast Moving Environment
A motivating example
What are the challenges?
◮ sampling new test labels for every measure is generally
expensive
Classification Labels in a Fast Moving Environment
A motivating example
What are the challenges?
◮ sampling new test labels for every measure is generally
expensive
◮ knowing how previous labels were sampled required to
optimally sample new items for test
Classification Labels in a Fast Moving Environment
A motivating example
What are the challenges?
◮ sampling new test labels for every measure is generally
expensive
◮ knowing how previous labels were sampled required to
optimally sample new items for test
◮ computing accuracy using all labels requires knowledge of
sampling profile
Classification Labels in a Fast Moving Environment
A motivating example
What are the challenges?
◮ sampling new test labels for every measure is generally
expensive
◮ knowing how previous labels were sampled required to
optimally sample new items for test
◮ computing accuracy using all labels requires knowledge of
sampling profile
◮ overtime reusing labels can become very tricky
Classification Labels in a Fast Moving Environment
Evaluation framework
◮ pi is probability of item i to be selected for test (Bernoulli)
◮ each item carries pi and is marked if selected (store the
sampling profile)
◮ accuracy:
1
i selected
1
pi i selected
1
pi
½{˜yi =yi }
Classification Labels in a Fast Moving Environment
Evaluation framework
◮ pi is probability of item i to be selected for test (Bernoulli)
◮ each item carries pi and is marked if selected (store the
sampling profile)
◮ accuracy:
1
i selected
1
pi i selected
1
pi
½{˜yi =yi }
◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled
Classification Labels in a Fast Moving Environment
Evaluation framework
◮ pi is probability of item i to be selected for test (Bernoulli)
◮ each item carries pi and is marked if selected (store the
sampling profile)
◮ accuracy:
1
i selected
1
pi i selected
1
pi
½{˜yi =yi }
◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled
◮ all labels are used
Classification Labels in a Fast Moving Environment
Evaluation framework
◮ pi is probability of item i to be selected for test (Bernoulli)
◮ each item carries pi and is marked if selected (store the
sampling profile)
◮ accuracy:
1
i selected
1
pi i selected
1
pi
½{˜yi =yi }
◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled
◮ all labels are used
◮ with uniform sampling this is simply “standard” accuracy
Classification Labels in a Fast Moving Environment
Evaluation framework
◮ pi is probability of item i to be selected for test (Bernoulli)
◮ each item carries pi and is marked if selected (store the
sampling profile)
◮ accuracy:
1
i selected
1
pi i selected
1
pi
½{˜yi =yi }
◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled
◮ all labels are used
◮ with uniform sampling this is simply “standard” accuracy
◮ very closely related to importance sampling
Classification Labels in a Fast Moving Environment
Evaluation framework
given existing sampling pi and extra budget
how do we sample?
◮ minimize accuracy variance with budget constraint
◮ can be formulated as an optimization problem
◮ easy to solve
Classification Labels in a Fast Moving Environment
Evaluation framework
it works as you’d expect as budget grows:
p p
◮ new budget (blue) used more where pi is smaller
◮ given enough budget we obtain uniform sampling
Classification Labels in a Fast Moving Environment
Extensions
◮ framework works more generally for supervised learning
◮ framework can work with a wide range of different metrics
◮ optimal sampling can use model posterior to reduce variance
◮ this framework can be used on the training side together with
active learning

Contenu connexe

Tendances

Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...
Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...
Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...Gaurav Singh Rajput
 
Experiences with Semi-Scripted Exploratory Testing
Experiences with Semi-Scripted Exploratory TestingExperiences with Semi-Scripted Exploratory Testing
Experiences with Semi-Scripted Exploratory TestingSimon Morley
 
Lifelong Analysis Skills for Explorers and Process Junkies alike!
Lifelong Analysis Skills for Explorers and Process Junkies alike!Lifelong Analysis Skills for Explorers and Process Junkies alike!
Lifelong Analysis Skills for Explorers and Process Junkies alike!Simon Morley
 
A Guide to the Five Whys Technique
A Guide to the Five Whys TechniqueA Guide to the Five Whys Technique
A Guide to the Five Whys TechniqueOlivier Serrat
 
HR Analysis: Really Cool Analytical Tools
HR Analysis: Really Cool Analytical ToolsHR Analysis: Really Cool Analytical Tools
HR Analysis: Really Cool Analytical Toolsmikeharmer
 
Failing: The Very Human Side of Testing
Failing: The Very Human Side of TestingFailing: The Very Human Side of Testing
Failing: The Very Human Side of TestingSimon Morley
 
5 why analysis training presentaion
5 why analysis training presentaion5 why analysis training presentaion
5 why analysis training presentaionDharmesh Panchal
 
Testing for everyone agile yorkshire
Testing for everyone agile yorkshireTesting for everyone agile yorkshire
Testing for everyone agile yorkshireAdy Stokes
 
Asking Questions and Writing Effectively
Asking Questions and Writing EffectivelyAsking Questions and Writing Effectively
Asking Questions and Writing EffectivelyChristopher Lopez
 
User Research @ Bitspiration2013
User Research @ Bitspiration2013User Research @ Bitspiration2013
User Research @ Bitspiration2013BDressler
 
4YFN 2016 Guerrilla UX
4YFN 2016 Guerrilla UX4YFN 2016 Guerrilla UX
4YFN 2016 Guerrilla UXSarah Rink
 
Hypothesis testing
Hypothesis testingHypothesis testing
Hypothesis testingArnab Sadhu
 
Beyond the (Survey) Monkey Business
Beyond the (Survey) Monkey BusinessBeyond the (Survey) Monkey Business
Beyond the (Survey) Monkey BusinessJo Flick
 

Tendances (19)

Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...
Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...
Root Cause Analysis | 5 whys | Tools of accident investigation I Gaurav Singh...
 
Experiences with Semi-Scripted Exploratory Testing
Experiences with Semi-Scripted Exploratory TestingExperiences with Semi-Scripted Exploratory Testing
Experiences with Semi-Scripted Exploratory Testing
 
Lifelong Analysis Skills for Explorers and Process Junkies alike!
Lifelong Analysis Skills for Explorers and Process Junkies alike!Lifelong Analysis Skills for Explorers and Process Junkies alike!
Lifelong Analysis Skills for Explorers and Process Junkies alike!
 
A Guide to the Five Whys Technique
A Guide to the Five Whys TechniqueA Guide to the Five Whys Technique
A Guide to the Five Whys Technique
 
HR Analysis: Really Cool Analytical Tools
HR Analysis: Really Cool Analytical ToolsHR Analysis: Really Cool Analytical Tools
HR Analysis: Really Cool Analytical Tools
 
5 whys
5 whys5 whys
5 whys
 
Failing: The Very Human Side of Testing
Failing: The Very Human Side of TestingFailing: The Very Human Side of Testing
Failing: The Very Human Side of Testing
 
5 why analysis training presentaion
5 why analysis training presentaion5 why analysis training presentaion
5 why analysis training presentaion
 
Testing for everyone agile yorkshire
Testing for everyone agile yorkshireTesting for everyone agile yorkshire
Testing for everyone agile yorkshire
 
Asking Questions and Writing Effectively
Asking Questions and Writing EffectivelyAsking Questions and Writing Effectively
Asking Questions and Writing Effectively
 
5 why analysis
5 why analysis5 why analysis
5 why analysis
 
5 whys
5 whys5 whys
5 whys
 
5 why analysis
5 why analysis5 why analysis
5 why analysis
 
Why why analysis
Why why analysisWhy why analysis
Why why analysis
 
User Research @ Bitspiration2013
User Research @ Bitspiration2013User Research @ Bitspiration2013
User Research @ Bitspiration2013
 
4YFN 2016 Guerrilla UX
4YFN 2016 Guerrilla UX4YFN 2016 Guerrilla UX
4YFN 2016 Guerrilla UX
 
Root cause analysis using 5 whys
Root cause analysis using 5 whysRoot cause analysis using 5 whys
Root cause analysis using 5 whys
 
Hypothesis testing
Hypothesis testingHypothesis testing
Hypothesis testing
 
Beyond the (Survey) Monkey Business
Beyond the (Survey) Monkey BusinessBeyond the (Survey) Monkey Business
Beyond the (Survey) Monkey Business
 

En vedette

Ramaciotti digital media marketing 2012 9
Ramaciotti digital media marketing 2012 9Ramaciotti digital media marketing 2012 9
Ramaciotti digital media marketing 2012 9Max Ramaciotti
 
Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16
Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16
Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16MLconf
 
Starting a Taxonomy Project (Presented at SLA 2013 Conference)
Starting a Taxonomy Project (Presented at SLA 2013 Conference)Starting a Taxonomy Project (Presented at SLA 2013 Conference)
Starting a Taxonomy Project (Presented at SLA 2013 Conference)Miraida Morales
 
Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...
Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...
Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...MLconf
 
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15MLconf
 
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16MLconf
 
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15MLconf
 
Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...
Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...
Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...MLconf
 
Shop vertical classification - Meetup Presentation
Shop vertical classification - Meetup PresentationShop vertical classification - Meetup Presentation
Shop vertical classification - Meetup Presentationprevota
 
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...MLconf
 
Taxonomies for E-commerce
Taxonomies for E-commerceTaxonomies for E-commerce
Taxonomies for E-commerceHeather Hedden
 
7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...
7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...
7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...Robson Motta
 

En vedette (12)

Ramaciotti digital media marketing 2012 9
Ramaciotti digital media marketing 2012 9Ramaciotti digital media marketing 2012 9
Ramaciotti digital media marketing 2012 9
 
Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16
Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16
Geetu Ambwani, Principal Data Scientist, Huffington Post at MLconf NYC - 4/15/16
 
Starting a Taxonomy Project (Presented at SLA 2013 Conference)
Starting a Taxonomy Project (Presented at SLA 2013 Conference)Starting a Taxonomy Project (Presented at SLA 2013 Conference)
Starting a Taxonomy Project (Presented at SLA 2013 Conference)
 
Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...
Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...
Animashree Anandkumar, Electrical Engineering and CS Dept, UC Irvine at MLcon...
 
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
Narayanan Sundaram, Research Scientist, Intel Labs at MLconf SF - 11/13/15
 
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
 
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
Melanie Warrick, Deep Learning Engineer, Skymind.io at MLconf SF - 11/13/15
 
Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...
Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...
Justin Basilico, Research/ Engineering Manager at Netflix at MLconf SF - 11/1...
 
Shop vertical classification - Meetup Presentation
Shop vertical classification - Meetup PresentationShop vertical classification - Meetup Presentation
Shop vertical classification - Meetup Presentation
 
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
 
Taxonomies for E-commerce
Taxonomies for E-commerceTaxonomies for E-commerce
Taxonomies for E-commerce
 
7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...
7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...
7 Machine Learning techniques in pratice in a Startup (Robson Motta - WIAMS U...
 

Similaire à Alessandro Magnani, Data Scientist, @WalmartLabs at MLconf SF - 11/13/15

Intro to A/B Testing by Ever's Senior Product Manager
Intro to A/B Testing by Ever's Senior Product ManagerIntro to A/B Testing by Ever's Senior Product Manager
Intro to A/B Testing by Ever's Senior Product ManagerProduct School
 
A/B Testing: Common Pitfalls and How to Avoid Them
A/B Testing: Common Pitfalls and How to Avoid ThemA/B Testing: Common Pitfalls and How to Avoid Them
A/B Testing: Common Pitfalls and How to Avoid ThemIgor Karpov
 
Your A/B Tests are Lying to You
Your A/B Tests are Lying to YouYour A/B Tests are Lying to You
Your A/B Tests are Lying to YouJohn Clevenger
 
Your A/B Tests are Lying to You
Your A/B Tests are Lying to YouYour A/B Tests are Lying to You
Your A/B Tests are Lying to YouJohn Clevenger
 
Anton Muzhailo - Practical Test Process Improvement using ISTQB
Anton Muzhailo - Practical Test Process Improvement using ISTQBAnton Muzhailo - Practical Test Process Improvement using ISTQB
Anton Muzhailo - Practical Test Process Improvement using ISTQBIevgenii Katsan
 
Understanding the Validity of a LCA
Understanding the Validity of a LCAUnderstanding the Validity of a LCA
Understanding the Validity of a LCALaurel McEwen
 
Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...
Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...
Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...Ankita Kaul
 
Lecture9 conjoint analysis
Lecture9 conjoint analysisLecture9 conjoint analysis
Lecture9 conjoint analysisJameson Watts
 
Meta-Analyses in Experimentation: The Whats and Hows
Meta-Analyses in Experimentation: The Whats and HowsMeta-Analyses in Experimentation: The Whats and Hows
Meta-Analyses in Experimentation: The Whats and HowsVWO
 
"How we killed 80% of features and increased outcomes of a/b testing by 100%"...
"How we killed 80% of features and increased outcomes of a/b testing by 100%"..."How we killed 80% of features and increased outcomes of a/b testing by 100%"...
"How we killed 80% of features and increased outcomes of a/b testing by 100%"...Fwdays
 
Automated solutions for product and pricing research
Automated solutions for product and pricing researchAutomated solutions for product and pricing research
Automated solutions for product and pricing researchRay Poynter
 
Revisiting the Experimental Design Choices for Approaches for the Automated R...
Revisiting the Experimental Design Choices for Approaches for the Automated R...Revisiting the Experimental Design Choices for Approaches for the Automated R...
Revisiting the Experimental Design Choices for Approaches for the Automated R...SAIL_QU
 
Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them Optimizely
 
Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them Optimizely
 
2 anton muzhailo - formal test process improvement. how to invest to the te...
2   anton muzhailo - formal test process improvement. how to invest to the te...2   anton muzhailo - formal test process improvement. how to invest to the te...
2 anton muzhailo - formal test process improvement. how to invest to the te...Ievgenii Katsan
 
slide->title; ?>
slide->title; ?>slide->title; ?>
slide->title; ?>Shyam Singh
 
Data-Driven Decision Making by Expedia Sr PM
Data-Driven Decision Making by Expedia Sr PMData-Driven Decision Making by Expedia Sr PM
Data-Driven Decision Making by Expedia Sr PMProduct School
 
PREP Webinar June 18th 2015 06-18
PREP Webinar June 18th 2015 06-18PREP Webinar June 18th 2015 06-18
PREP Webinar June 18th 2015 06-18preprecyclability
 
Can I Test More Than One Variable at a Time? Statisticians answer some of th...
Can I Test More Than One Variable at a  Time? Statisticians answer some of th...Can I Test More Than One Variable at a  Time? Statisticians answer some of th...
Can I Test More Than One Variable at a Time? Statisticians answer some of th...MarketingExperiments
 

Similaire à Alessandro Magnani, Data Scientist, @WalmartLabs at MLconf SF - 11/13/15 (20)

Intro to A/B Testing by Ever's Senior Product Manager
Intro to A/B Testing by Ever's Senior Product ManagerIntro to A/B Testing by Ever's Senior Product Manager
Intro to A/B Testing by Ever's Senior Product Manager
 
A/B Testing: Common Pitfalls and How to Avoid Them
A/B Testing: Common Pitfalls and How to Avoid ThemA/B Testing: Common Pitfalls and How to Avoid Them
A/B Testing: Common Pitfalls and How to Avoid Them
 
Your A/B Tests are Lying to You
Your A/B Tests are Lying to YouYour A/B Tests are Lying to You
Your A/B Tests are Lying to You
 
Your A/B Tests are Lying to You
Your A/B Tests are Lying to YouYour A/B Tests are Lying to You
Your A/B Tests are Lying to You
 
Anton Muzhailo - Practical Test Process Improvement using ISTQB
Anton Muzhailo - Practical Test Process Improvement using ISTQBAnton Muzhailo - Practical Test Process Improvement using ISTQB
Anton Muzhailo - Practical Test Process Improvement using ISTQB
 
Understanding the Validity of a LCA
Understanding the Validity of a LCAUnderstanding the Validity of a LCA
Understanding the Validity of a LCA
 
Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...
Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...
Predicting Helpfulness of User-Generated Product Reviews Through Analytical M...
 
Lecture9 conjoint analysis
Lecture9 conjoint analysisLecture9 conjoint analysis
Lecture9 conjoint analysis
 
Meta-Analyses in Experimentation: The Whats and Hows
Meta-Analyses in Experimentation: The Whats and HowsMeta-Analyses in Experimentation: The Whats and Hows
Meta-Analyses in Experimentation: The Whats and Hows
 
"How we killed 80% of features and increased outcomes of a/b testing by 100%"...
"How we killed 80% of features and increased outcomes of a/b testing by 100%"..."How we killed 80% of features and increased outcomes of a/b testing by 100%"...
"How we killed 80% of features and increased outcomes of a/b testing by 100%"...
 
Automated solutions for product and pricing research
Automated solutions for product and pricing researchAutomated solutions for product and pricing research
Automated solutions for product and pricing research
 
Revisiting the Experimental Design Choices for Approaches for the Automated R...
Revisiting the Experimental Design Choices for Approaches for the Automated R...Revisiting the Experimental Design Choices for Approaches for the Automated R...
Revisiting the Experimental Design Choices for Approaches for the Automated R...
 
Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them
 
Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them Product Experimentation Pitfalls & How to Avoid Them
Product Experimentation Pitfalls & How to Avoid Them
 
2 anton muzhailo - formal test process improvement. how to invest to the te...
2   anton muzhailo - formal test process improvement. how to invest to the te...2   anton muzhailo - formal test process improvement. how to invest to the te...
2 anton muzhailo - formal test process improvement. how to invest to the te...
 
slide->title; ?>
slide->title; ?>slide->title; ?>
slide->title; ?>
 
KDD
KDDKDD
KDD
 
Data-Driven Decision Making by Expedia Sr PM
Data-Driven Decision Making by Expedia Sr PMData-Driven Decision Making by Expedia Sr PM
Data-Driven Decision Making by Expedia Sr PM
 
PREP Webinar June 18th 2015 06-18
PREP Webinar June 18th 2015 06-18PREP Webinar June 18th 2015 06-18
PREP Webinar June 18th 2015 06-18
 
Can I Test More Than One Variable at a Time? Statisticians answer some of th...
Can I Test More Than One Variable at a  Time? Statisticians answer some of th...Can I Test More Than One Variable at a  Time? Statisticians answer some of th...
Can I Test More Than One Variable at a Time? Statisticians answer some of th...
 

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

Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...apidays
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityWSO2
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMKumar Satyam
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamUiPathCommunity
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Zilliz
 

Dernier (20)

Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
WSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering DevelopersWSO2's API Vision: Unifying Control, Empowering Developers
WSO2's API Vision: Unifying Control, Empowering Developers
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDM
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 

Alessandro Magnani, Data Scientist, @WalmartLabs at MLconf SF - 11/13/15

  • 1. Classification Labels in a Fast Moving Environment Classification Labels in a Fast Moving Environment Alessandro Magnani @WalmartLabs, Walmart Global eCommerce California, USA Friday 13th November, 2015
  • 2. Classification Labels in a Fast Moving Environment Classification Model Performance Items Classifier Editor N sampled items true label yi estimate ˜yi accuracyEvaluation ◮ correctly evaluating classification models is critical and requires labels ◮ labeling products is expensive ◮ need to correctly and optimally use labels
  • 3. Classification Labels in a Fast Moving Environment Classification Model Performance Items Classifier Editor N sampled items true label yi estimate ˜yi accuracyEvaluation Measure accuracy common approach: ◮ sample uniformly at random N items ◮ compute accuracy 1 N N i=1 ½{˜yi =yi }
  • 4. Classification Labels in a Fast Moving Environment Practical challenges Items Classifier Editor N sampled items true label yi estimate ˜yi accuracyEvaluation ◮ items change over time
  • 5. Classification Labels in a Fast Moving Environment Practical challenges Items Classifier Editor N sampled items true label yi estimate ˜yi accuracyEvaluation ◮ items change over time ◮ evaluation required over multiple subsets
  • 6. Classification Labels in a Fast Moving Environment Practical challenges Items Classifier Editor N sampled items true label yi estimate ˜yi accuracyEvaluation ◮ items change over time ◮ evaluation required over multiple subsets ◮ existing labels potentially hard to reuse
  • 7. Classification Labels in a Fast Moving Environment A motivating example compute accuracy over 1M items 1K labels budget ◮ sample 1K items and get labels yi ◮ measure accuracy 1 1K 1K i=1 ½{˜yi =yi } 1M p 1 1K
  • 8. Classification Labels in a Fast Moving Environment A motivating example 500K items added, compute accuracy on all 1.5M items ◮ use previous accuracy measure ◮ most likely inaccurate 1M 1.5M p 1 1K
  • 9. Classification Labels in a Fast Moving Environment A motivating example 500K items added, compute accuracy on all 1.5M items 500 labels extra budget ◮ sample 500 items from the 1.5M ◮ compute accuracy on new 500 labels ◮ previous 1K labels “wasted” 1M 1.5M p 1 3K
  • 10. Classification Labels in a Fast Moving Environment A motivating example 500K items added, compute accuracy on all 1.5M items 500 labels extra budget, better approach ◮ sample 500 items from new items ◮ compute accuracy on all 1.5K labels ◮ no label “wasted” 1M 1.5M p 1 1K
  • 11. Classification Labels in a Fast Moving Environment A motivating example 500K items added, compute accuracy on all 1.5M items only 250 labels extra budget? ◮ sample 250 items from new items ◮ need to account for difference in sampling ◮ accuracy: 1M 1.5M p 1 2K 1 1.5K 1K i=1 ½{˜yi =yi } + 2 250 i=1 ½{˜ynew i =ynew i }
  • 12. Classification Labels in a Fast Moving Environment A motivating example What are the challenges? ◮ sampling new test labels for every measure is generally expensive
  • 13. Classification Labels in a Fast Moving Environment A motivating example What are the challenges? ◮ sampling new test labels for every measure is generally expensive ◮ knowing how previous labels were sampled required to optimally sample new items for test
  • 14. Classification Labels in a Fast Moving Environment A motivating example What are the challenges? ◮ sampling new test labels for every measure is generally expensive ◮ knowing how previous labels were sampled required to optimally sample new items for test ◮ computing accuracy using all labels requires knowledge of sampling profile
  • 15. Classification Labels in a Fast Moving Environment A motivating example What are the challenges? ◮ sampling new test labels for every measure is generally expensive ◮ knowing how previous labels were sampled required to optimally sample new items for test ◮ computing accuracy using all labels requires knowledge of sampling profile ◮ overtime reusing labels can become very tricky
  • 16. Classification Labels in a Fast Moving Environment Evaluation framework ◮ pi is probability of item i to be selected for test (Bernoulli) ◮ each item carries pi and is marked if selected (store the sampling profile) ◮ accuracy: 1 i selected 1 pi i selected 1 pi ½{˜yi =yi }
  • 17. Classification Labels in a Fast Moving Environment Evaluation framework ◮ pi is probability of item i to be selected for test (Bernoulli) ◮ each item carries pi and is marked if selected (store the sampling profile) ◮ accuracy: 1 i selected 1 pi i selected 1 pi ½{˜yi =yi } ◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled
  • 18. Classification Labels in a Fast Moving Environment Evaluation framework ◮ pi is probability of item i to be selected for test (Bernoulli) ◮ each item carries pi and is marked if selected (store the sampling profile) ◮ accuracy: 1 i selected 1 pi i selected 1 pi ½{˜yi =yi } ◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled ◮ all labels are used
  • 19. Classification Labels in a Fast Moving Environment Evaluation framework ◮ pi is probability of item i to be selected for test (Bernoulli) ◮ each item carries pi and is marked if selected (store the sampling profile) ◮ accuracy: 1 i selected 1 pi i selected 1 pi ½{˜yi =yi } ◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled ◮ all labels are used ◮ with uniform sampling this is simply “standard” accuracy
  • 20. Classification Labels in a Fast Moving Environment Evaluation framework ◮ pi is probability of item i to be selected for test (Bernoulli) ◮ each item carries pi and is marked if selected (store the sampling profile) ◮ accuracy: 1 i selected 1 pi i selected 1 pi ½{˜yi =yi } ◮ for evaluation to be possible pj > 0 for all j labeled/unlabeled ◮ all labels are used ◮ with uniform sampling this is simply “standard” accuracy ◮ very closely related to importance sampling
  • 21. Classification Labels in a Fast Moving Environment Evaluation framework given existing sampling pi and extra budget how do we sample? ◮ minimize accuracy variance with budget constraint ◮ can be formulated as an optimization problem ◮ easy to solve
  • 22. Classification Labels in a Fast Moving Environment Evaluation framework it works as you’d expect as budget grows: p p ◮ new budget (blue) used more where pi is smaller ◮ given enough budget we obtain uniform sampling
  • 23. Classification Labels in a Fast Moving Environment Extensions ◮ framework works more generally for supervised learning ◮ framework can work with a wide range of different metrics ◮ optimal sampling can use model posterior to reduce variance ◮ this framework can be used on the training side together with active learning