SlideShare una empresa de Scribd logo
1 de 38
Descargar para leer sin conexión
When
Recommendation
Systems Go Bad
Evan Estola
12/10/15
About Me
● Evan Estola
● Senior Machine Learning Engineer @ Meetup
● evan@meetup.com
● @estola
Agenda
1. Meetup
2. Recommendation Systems
3. What can go wrong?
4. How to prevent it
We want a world full of real, local community.
Women’s Veterans Meetup, San Antonio, TX
Recommendation Systems: Collaborative Filtering
You just wanted a
kitchen scale, now
Amazon thinks you’re
a drug dealer
Recommendation Systems: Rating Prediction
● Netflix prize
● How many stars would user X give movie Y
● Boring
Recommendation Systems: Learning To Rank
● Active area of research
● Use ML model to solve a ranking problem
● Pointwise: Logistic Regression on binary label, use output for ranking
● Listwise: Optimize entire list
● Performance Metrics
○ Mean Average Precision
○ P@K
○ Discounted Cumulative Gain
Data
Science
impacts
lives
● News you’re exposed to
● Friend’s Activity/Facebook feed
● Job openings you find/get
● If you can get a loan
● Route you take to get somewhere
● If you can get a ride
● Movies you watch on Netflix
● Products you buy on Amazon
● Price you pay for things
● If a product is available to you at all
● Apps you download
● Ads you see
Ego
● Member/customer/user first
● Focus on building the best product,
not on being the most clever data
scientist
● Much harder to spin a positive user
story than a story about how smart
you are
●
● Fake profiles, track ads
● Career coaching for “200k+”
Executive jobs Ad
● Male group: 1852 impressions
● Female group: 318
● “Black-sounding” names 25% more
likely to be served ad suggesting
criminal record
Ethics
We have accepted that Machine Learning
can seem creepy, how do we prevent it
from becoming immoral?
We have an ethical obligation to not
teach machines to be prejudiced.
Data
Ethics
Awareness
● Tell your friends
● Tell your coworkers
● Tell your boss
Awareness
● Start a conversation
○ Identify potentially marginalized user groups
○ Have an ethics strategy for evaluating whether to include
sensitive features
Interpretable
Models
● For simple problems, simple
solutions are often worth a small
concession in performance
● Inspectable models make it easier
to debug problems in data
collection, feature engineering etc.
● Only include features that work the
way you want
● Don’t include feature interactions
that you don’t want
Logistic Regression
StraightDistanceFeature(-0.0311f),
ChapterZipScore(0.0250f),
RsvpCountFeature(0.0207f),
AgeUnmatchFeature(-1.5876f),
GenderUnmatchFeature(-3.0459f),
StateMatchFeature(0.4931f),
CountryMatchFeature(0.5735f),
FacebookFriendsFeature(1.9617f),
SecondDegreeFacebookFriendsFeature(0.1594f),
ApproxAgeUnmatchFeature(-0.2986f),
SensitiveUnmatchFeature(-0.1937f),
KeywordTopicScoreFeatureNoSuppressed(4.2432f),
TopicScoreBucketFeatureNoSuppressed(1.4469f,0.257f,10f),
TopicScoreBucketFeatureSuppressed(0.2595f,0.099f,10f),
ExtendedTopicsBucketFeatureNoSuppressed(1.6203f,1.091f,10f),
ChapterRelatedTopicsBucketFeatureNoSuppressed(0.1702f,0.252f,0.641f),
ChapterRelatedTopicsBucketFeatureNoSuppressed(0.4983f,0.641f,10f),
DoneChapterTopicsFeatureNoSuppressed(3.3367f)
Feature Engineering and Interactions
● Good Feature:
○ Join! You’re interested in Tech x Meetup is about Tech
● Good Feature:
○ Don’t join! Group is intended only for Women x You are a Man
● Bad Feature:
○ Don’t join! Group is mostly Men x You are a Woman
● Horrible Feature:
○ Don’t join! Meetup is about Tech x You are a Woman
Meetup is not interested in propagating gender stereotypes
Ensemble
Models and
Data
segregation
Ensemble Models: Combine outputs of
several classifiers for increased accuracy
If you have features that are useful but
you’re worried about interaction (and
your model does it automatically) use
ensemble modeling to restrict the
features to separate models.
Ensemble Model, Data Segregation
Data:
*Interests
Searches
Friends
Location
Data:
*Gender
Friends
Location
Data:
Model1 Prediction
Model2 Prediction
Model1 Prediction
Model2 Prediction
Final Prediction
Diversity
controlled
test data
● Make sure product works for
everybody
● Generate test data and evaluate
your model against it to confirm no
encapsulated prejudice
Diversity Controlled Testing
● CMU - AdFisher
○ Crawls ads with simulated user profiles
● Same technique can work to find bias in your own models!
○ Generate Test Data
■ Randomize sensitive feature in real data set
○ Run Model
■ Evaluate for unacceptable biased treatment
● Must identify what features are sensitive and what outcomes are
unwanted
You know racist computers are a
bad idea
Don’t let your company invent
racist computers

Más contenido relacionado

Destacado

Soalan mate year 4 paper 2 july
Soalan mate year 4 paper 2 julySoalan mate year 4 paper 2 july
Soalan mate year 4 paper 2 july
Azli Bakar
 
BACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSE
BACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSEBACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSE
BACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSE
Diana Agudelo
 
GWC2013 - Berni Melero - Canal + - Engaging with Game of Thrones
GWC2013 - Berni Melero - Canal + - Engaging with Game of ThronesGWC2013 - Berni Melero - Canal + - Engaging with Game of Thrones
GWC2013 - Berni Melero - Canal + - Engaging with Game of Thrones
gamificationworldcongress
 
Presentasjon om biler
Presentasjon om bilerPresentasjon om biler
Presentasjon om biler
Abdelhay1961
 
Presentasjon om biler2
Presentasjon om biler2Presentasjon om biler2
Presentasjon om biler2
Abdelhay1961
 

Destacado (20)

Deep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image GenerationDeep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image Generation
 
GWC14: Jaume Juan - "Challenge: An incredible Game Dynamic for Massive Learning"
GWC14: Jaume Juan - "Challenge: An incredible Game Dynamic for Massive Learning"GWC14: Jaume Juan - "Challenge: An incredible Game Dynamic for Massive Learning"
GWC14: Jaume Juan - "Challenge: An incredible Game Dynamic for Massive Learning"
 
Water bobble
Water bobbleWater bobble
Water bobble
 
Court system
Court systemCourt system
Court system
 
Media, marki, prowokacje
Media, marki, prowokacjeMedia, marki, prowokacje
Media, marki, prowokacje
 
TPC CONCEPT One to One Training
TPC CONCEPT One to One TrainingTPC CONCEPT One to One Training
TPC CONCEPT One to One Training
 
Soalan mate year 4 paper 2 july
Soalan mate year 4 paper 2 julySoalan mate year 4 paper 2 july
Soalan mate year 4 paper 2 july
 
Nelly romano.ppt
Nelly romano.pptNelly romano.ppt
Nelly romano.ppt
 
BACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSE
BACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSEBACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSE
BACTERIAS INFECTION AND IMMUNE SYSTEM RESPONSE
 
GWC2013 - Berni Melero - Canal + - Engaging with Game of Thrones
GWC2013 - Berni Melero - Canal + - Engaging with Game of ThronesGWC2013 - Berni Melero - Canal + - Engaging with Game of Thrones
GWC2013 - Berni Melero - Canal + - Engaging with Game of Thrones
 
Presentación Club Autopremio
Presentación Club AutopremioPresentación Club Autopremio
Presentación Club Autopremio
 
Presentasi kelas holcim oke
Presentasi kelas holcim okePresentasi kelas holcim oke
Presentasi kelas holcim oke
 
Presentasjon om biler
Presentasjon om bilerPresentasjon om biler
Presentasjon om biler
 
Presentasjon om biler2
Presentasjon om biler2Presentasjon om biler2
Presentasjon om biler2
 
PNPM-MP dari perspektif Akademisi
PNPM-MP dari perspektif AkademisiPNPM-MP dari perspektif Akademisi
PNPM-MP dari perspektif Akademisi
 
2011 Wright County Iowa Laborshed Summary
2011 Wright County Iowa Laborshed Summary2011 Wright County Iowa Laborshed Summary
2011 Wright County Iowa Laborshed Summary
 
2011 Calhoun County Iowa Laborshed Summary
2011 Calhoun County Iowa Laborshed Summary2011 Calhoun County Iowa Laborshed Summary
2011 Calhoun County Iowa Laborshed Summary
 
Civil Rights = Labor Unions
Civil Rights = Labor UnionsCivil Rights = Labor Unions
Civil Rights = Labor Unions
 
GWC14: Victor manrique - "How successful gamified experiences are designed"
GWC14: Victor manrique - "How successful gamified experiences are designed"GWC14: Victor manrique - "How successful gamified experiences are designed"
GWC14: Victor manrique - "How successful gamified experiences are designed"
 
Zurawski2013cv
Zurawski2013cvZurawski2013cv
Zurawski2013cv
 

Similar a When recommendation systems go bad

Similar a When recommendation systems go bad (20)

When recommendation go bad
When recommendation go badWhen recommendation go bad
When recommendation go bad
 
When recommendation systems go bad - machine eatable
When recommendation systems go bad - machine eatableWhen recommendation systems go bad - machine eatable
When recommendation systems go bad - machine eatable
 
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
GIAF UK Winter 2015 - Analytical techniques: A practical guide to answering b...
 
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
Evan Estola, Lead Machine Learning Engineer, Meetup at MLconf SEA - 5/20/16
 
Offline evaluation of recommender systems: all pain and no gain?
Offline evaluation of recommender systems: all pain and no gain?Offline evaluation of recommender systems: all pain and no gain?
Offline evaluation of recommender systems: all pain and no gain?
 
How tech startups can leverage data analytics and visualization
How tech startups can leverage data analytics and visualizationHow tech startups can leverage data analytics and visualization
How tech startups can leverage data analytics and visualization
 
Recommendation engine Using Genetic Algorithm
Recommendation engine Using Genetic AlgorithmRecommendation engine Using Genetic Algorithm
Recommendation engine Using Genetic Algorithm
 
What We Learned from Three Years of Sciencing the Crap Out of DevOps
What We Learned from Three Years of Sciencing the Crap Out of DevOpsWhat We Learned from Three Years of Sciencing the Crap Out of DevOps
What We Learned from Three Years of Sciencing the Crap Out of DevOps
 
What We Learned from Three Years of Sciencing the Crap Out of DevOps
What We Learned from Three Years of Sciencing the Crap Out of DevOpsWhat We Learned from Three Years of Sciencing the Crap Out of DevOps
What We Learned from Three Years of Sciencing the Crap Out of DevOps
 
What we learned from three years sciencing the crap out of devops
What we learned from three years sciencing the crap out of devopsWhat we learned from three years sciencing the crap out of devops
What we learned from three years sciencing the crap out of devops
 
What Are the Basics of Product Manager Interviews by Google PM
What Are the Basics of Product Manager Interviews by Google PMWhat Are the Basics of Product Manager Interviews by Google PM
What Are the Basics of Product Manager Interviews by Google PM
 
Cole Napper: Orgnostic's people analytics and employee listening strategy to ...
Cole Napper: Orgnostic's people analytics and employee listening strategy to ...Cole Napper: Orgnostic's people analytics and employee listening strategy to ...
Cole Napper: Orgnostic's people analytics and employee listening strategy to ...
 
Data Science Workshop - day 2
Data Science Workshop - day 2Data Science Workshop - day 2
Data Science Workshop - day 2
 
Data science Applications in the Enterprise
Data science Applications in the EnterpriseData science Applications in the Enterprise
Data science Applications in the Enterprise
 
Module 7: Unsupervised Learning
Module 7:  Unsupervised LearningModule 7:  Unsupervised Learning
Module 7: Unsupervised Learning
 
How ml can improve purchase conversions
How ml can improve purchase conversionsHow ml can improve purchase conversions
How ml can improve purchase conversions
 
UK GIAF: Winter 2015
UK GIAF: Winter 2015UK GIAF: Winter 2015
UK GIAF: Winter 2015
 
How to Build Customer Centric Products by Microsoft Senior PM
How to Build Customer Centric Products by Microsoft Senior PMHow to Build Customer Centric Products by Microsoft Senior PM
How to Build Customer Centric Products by Microsoft Senior PM
 
Recent Trends in Personalization at Netflix
Recent Trends in Personalization at NetflixRecent Trends in Personalization at Netflix
Recent Trends in Personalization at Netflix
 
Start With Why: Build Product Progress with a Strong Data Culture
Start With Why: Build Product Progress with a Strong Data CultureStart With Why: Build Product Progress with a Strong Data Culture
Start With Why: Build Product Progress with a Strong Data Culture
 

Último

Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Victor Rentea
 

Último (20)

Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdf
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
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 ...
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Ransomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdfRansomware_Q4_2023. The report. [EN].pdf
Ransomware_Q4_2023. The report. [EN].pdf
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
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
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
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 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 

When recommendation systems go bad