SlideShare a Scribd company logo
1 of 49
Download to read offline
Friederike Schüür
Research Engineer
@FSchueuer
fastforwardlabs.com
contact@fastforwardlabs.com
@FastForwardLabs
http://blog.fastforwardlabs.com/2017/08/02/interpretability.html
http://blog.fastforwardlabs.com/2017/09/01/LIME-for-couples.html
Why your relationship is likely to last, or not?
Why your relationship is likely to last, or not?
we predict
https://www.newyorker.com/cartoon/a19697
Algorithms decide which emails
reach our inboxes, whether we are
approved for credit, and whom we
get the opportunity to date.
But, as algorithms give answers,
they raise questions. If an algorithm
denies your loan application,
wouldn’t you like to know why or
what you could change for a more
positive outcome?
Or perhaps you’d like to know if
your bank is right to trust the
algorithm in the first place.
We need models that we know are right for the
right reasons and wrong for the right reasons.
Traditional model
validation only tells us
how well we do on the
holdout validation set.
It does not tell us whether
we are right for the right
reasons and wrong for
the right reasons.
This model is “right”
(i.e., scores high on
the holdout
validation set) for
the wrong reasons.
Knowing the reasons for a
prediction may also provide
us with strategies to change
the predicted outcome.
The Benefits of Interpretability
• Verify the model is right for the right reasons and wrong for the
right reasons (and develop trust in the model).
• Explain individual model decisions and guide intervention.
• Satisfy regulators and ethical concerns (in EU: GDPR in May 2018).
• Develop a more collaborative relationship with models (AI)
Accuracy -
Interpretability tradeoff:
accurate models tend to
be less interpretable.
Accuracy -
Interpretability tradeoff:
accurate models tend to
be less interpretable.
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
Model-agnostic
interpretability: Local
Interpretable Model
Explanations (LIME).
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
https://arxiv.org/abs/1602.04938 https://github.com/marcotcr/lime
http://blog.fastforwardlabs.com/2017/09/01/LIME-for-couples.html
https://data.stanford.edu/hcmst
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
Instantiate the LIME explainer object:
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
Explain an individual prediction:
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
Get an explanation (alongside prediction):
Let’s take a closer look:
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
Let’s construct a data preprocessing pipeline:
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
And then train the model:
Interpretable feature as inputs to pipeline:
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
Can I use LIME for (algorithmic)
relationship advice?
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
Currently, we’re at 0.73 chance:
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
But hey, I just got a raise!
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
What if we bought our apartment?
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
Really, we should just get married:
Data are traces of past activity.
Behavioral data encode past behavioral patterns,
some of which reflect outdated conventions,
prejudice, or harmful past practices.
https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb
https://www.propublica.org/article/machine-bias-risk-
assessments-in-criminal-sentencing
The Benefits of Interpretability
• Verify the model is right for the right reasons and wrong for the
right reasons (and develop trust in the model).
• Explain individual model decisions and guide intervention.
• Satisfy regulators and ethical concerns (in EU: GDPR in May 2018).
• Develop a more collaborative relationship with models (AI)
The Benefits of LIME
• Model-agnostic interpretability solutions like LIME avoid the
interpretability-accuracy trade off.
• Model-agnostic interpretability solutions like LIME work with any model,
even the ones already trained.
• LIME is easy to use, it can extend any machine learning pipeline.
• LIME works best with tabular data (continuous and categorical).
Resources
• Blog post (http://blog.fastforwardlabs.com/2017/09/01/LIME-for-couples.html) and
notebook (https://github.com/fastforwardlabs/couples-lime/blob/master/couples-lime.ipynb)
• LIME paper (https://arxiv.org/abs/1602.04938) and code (https://github.com/marcotcr/lime).
• Machine bias and recidivism (https://www.propublica.org/article/machine-bias-risk-
assessments-in-criminal-sentencing).
• Interpretability via influence functions (https://arxiv.org/abs/1703.04730).
• Attention layers in neural networks (e.g., http://www.cs.cmu.edu/~./hovy/papers/16HLT-
hierarchical-attention-networks.pdf).
• Research and conference on Fairness, Accountability, and Transparency in ML (https://
www.fatml.org/).

More Related Content

Similar to Why your relationship is likely to last, or not: Local Interpretable Model-Agnostic Explanations

Top 5 Tips for Building Viral Social Web Applications and Sites
Top 5 Tips for Building Viral Social Web Applications and SitesTop 5 Tips for Building Viral Social Web Applications and Sites
Top 5 Tips for Building Viral Social Web Applications and Sites
Jonathan LeBlanc
 

Similar to Why your relationship is likely to last, or not: Local Interpretable Model-Agnostic Explanations (20)

Experiments in Data Portability 2
Experiments in Data Portability 2Experiments in Data Portability 2
Experiments in Data Portability 2
 
Finding harmony in web development
Finding harmony in web developmentFinding harmony in web development
Finding harmony in web development
 
Big Data Week 2013 Flow
Big Data Week 2013 FlowBig Data Week 2013 Flow
Big Data Week 2013 Flow
 
FFWD.PRO - It's not you, It's me (or how to avoid being coupled with a Javasc...
FFWD.PRO - It's not you, It's me (or how to avoid being coupled with a Javasc...FFWD.PRO - It's not you, It's me (or how to avoid being coupled with a Javasc...
FFWD.PRO - It's not you, It's me (or how to avoid being coupled with a Javasc...
 
Working In The Now - Paris Web
Working In The Now - Paris WebWorking In The Now - Paris Web
Working In The Now - Paris Web
 
Travailler dans le présent - Chris Heilmann - Paris Web 2008
Travailler dans le présent - Chris Heilmann - Paris Web 2008Travailler dans le présent - Chris Heilmann - Paris Web 2008
Travailler dans le présent - Chris Heilmann - Paris Web 2008
 
Google Machine Learning Algorithms and SEO
Google Machine Learning Algorithms and SEOGoogle Machine Learning Algorithms and SEO
Google Machine Learning Algorithms and SEO
 
Disclosing password hashing policies
Disclosing password hashing policiesDisclosing password hashing policies
Disclosing password hashing policies
 
Resisting The Feature Creature
Resisting The Feature CreatureResisting The Feature Creature
Resisting The Feature Creature
 
BrightonSEO October 2022 - Martijn Scheybeler - SEO Testing: Find Out What Wo...
BrightonSEO October 2022 - Martijn Scheybeler - SEO Testing: Find Out What Wo...BrightonSEO October 2022 - Martijn Scheybeler - SEO Testing: Find Out What Wo...
BrightonSEO October 2022 - Martijn Scheybeler - SEO Testing: Find Out What Wo...
 
Walter api
Walter apiWalter api
Walter api
 
Top 5 Tips for Building Viral Social Web Applications and Sites
Top 5 Tips for Building Viral Social Web Applications and SitesTop 5 Tips for Building Viral Social Web Applications and Sites
Top 5 Tips for Building Viral Social Web Applications and Sites
 
Patterns of Semantic Integration
Patterns of Semantic IntegrationPatterns of Semantic Integration
Patterns of Semantic Integration
 
Unlocking the Power of ChatGPT
Unlocking the Power of ChatGPTUnlocking the Power of ChatGPT
Unlocking the Power of ChatGPT
 
Social Media Analytics using Amazon QuickSight - AWS Online Tech Talks
Social Media Analytics using Amazon QuickSight - AWS Online Tech TalksSocial Media Analytics using Amazon QuickSight - AWS Online Tech Talks
Social Media Analytics using Amazon QuickSight - AWS Online Tech Talks
 
How to connect social media with open standards
How to connect social media with open standardsHow to connect social media with open standards
How to connect social media with open standards
 
Updates on Offline: “My AppCache won’t come back” and “ServiceWorker Tricks ...
Updates on Offline: “My AppCache won’t come back” and  “ServiceWorker Tricks ...Updates on Offline: “My AppCache won’t come back” and  “ServiceWorker Tricks ...
Updates on Offline: “My AppCache won’t come back” and “ServiceWorker Tricks ...
 
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
All in AI: LLM Landscape & RAG in 2024 with Mark Ryan (Google) & Jerry Liu (L...
 
Anatomy of Java Vulnerabilities - NLJug 2018
Anatomy of Java Vulnerabilities - NLJug 2018Anatomy of Java Vulnerabilities - NLJug 2018
Anatomy of Java Vulnerabilities - NLJug 2018
 
How I built the demo's
How I built the demo'sHow I built the demo's
How I built the demo's
 

More from PyData

More from PyData (20)

Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
Michal Mucha: Build and Deploy an End-to-end Streaming NLP Insight System | P...
 
Unit testing data with marbles - Jane Stewart Adams, Leif Walsh
Unit testing data with marbles - Jane Stewart Adams, Leif WalshUnit testing data with marbles - Jane Stewart Adams, Leif Walsh
Unit testing data with marbles - Jane Stewart Adams, Leif Walsh
 
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake BolewskiThe TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
The TileDB Array Data Storage Manager - Stavros Papadopoulos, Jake Bolewski
 
Using Embeddings to Understand the Variance and Evolution of Data Science... ...
Using Embeddings to Understand the Variance and Evolution of Data Science... ...Using Embeddings to Understand the Variance and Evolution of Data Science... ...
Using Embeddings to Understand the Variance and Evolution of Data Science... ...
 
Deploying Data Science for Distribution of The New York Times - Anne Bauer
Deploying Data Science for Distribution of The New York Times - Anne BauerDeploying Data Science for Distribution of The New York Times - Anne Bauer
Deploying Data Science for Distribution of The New York Times - Anne Bauer
 
Graph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
Graph Analytics - From the Whiteboard to Your Toolbox - Sam LermaGraph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
Graph Analytics - From the Whiteboard to Your Toolbox - Sam Lerma
 
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
Do Your Homework! Writing tests for Data Science and Stochastic Code - David ...
 
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo MazzaferroRESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
RESTful Machine Learning with Flask and TensorFlow Serving - Carlo Mazzaferro
 
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
Mining dockless bikeshare and dockless scootershare trip data - Stefanie Brod...
 
Avoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
Avoiding Bad Database Surprises: Simulation and Scalability - Steven LottAvoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
Avoiding Bad Database Surprises: Simulation and Scalability - Steven Lott
 
Words in Space - Rebecca Bilbro
Words in Space - Rebecca BilbroWords in Space - Rebecca Bilbro
Words in Space - Rebecca Bilbro
 
End-to-End Machine learning pipelines for Python driven organizations - Nick ...
End-to-End Machine learning pipelines for Python driven organizations - Nick ...End-to-End Machine learning pipelines for Python driven organizations - Nick ...
End-to-End Machine learning pipelines for Python driven organizations - Nick ...
 
Pydata beautiful soup - Monica Puerto
Pydata beautiful soup - Monica PuertoPydata beautiful soup - Monica Puerto
Pydata beautiful soup - Monica Puerto
 
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
 
Extending Pandas with Custom Types - Will Ayd
Extending Pandas with Custom Types - Will AydExtending Pandas with Custom Types - Will Ayd
Extending Pandas with Custom Types - Will Ayd
 
Measuring Model Fairness - Stephen Hoover
Measuring Model Fairness - Stephen HooverMeasuring Model Fairness - Stephen Hoover
Measuring Model Fairness - Stephen Hoover
 
What's the Science in Data Science? - Skipper Seabold
What's the Science in Data Science? - Skipper SeaboldWhat's the Science in Data Science? - Skipper Seabold
What's the Science in Data Science? - Skipper Seabold
 
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
Applying Statistical Modeling and Machine Learning to Perform Time-Series For...
 
Solving very simple substitution ciphers algorithmically - Stephen Enright-Ward
Solving very simple substitution ciphers algorithmically - Stephen Enright-WardSolving very simple substitution ciphers algorithmically - Stephen Enright-Ward
Solving very simple substitution ciphers algorithmically - Stephen Enright-Ward
 
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
The Face of Nanomaterials: Insightful Classification Using Deep Learning - An...
 

Recently uploaded

CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)
Wonjun Hwang
 
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptxHarnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
FIDO Alliance
 

Recently uploaded (20)

CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)
 
AI mind or machine power point presentation
AI mind or machine power point presentationAI mind or machine power point presentation
AI mind or machine power point presentation
 
Overview of Hyperledger Foundation
Overview of Hyperledger FoundationOverview of Hyperledger Foundation
Overview of Hyperledger Foundation
 
Introduction to FIDO Authentication and Passkeys.pptx
Introduction to FIDO Authentication and Passkeys.pptxIntroduction to FIDO Authentication and Passkeys.pptx
Introduction to FIDO Authentication and Passkeys.pptx
 
ADP Passwordless Journey Case Study.pptx
ADP Passwordless Journey Case Study.pptxADP Passwordless Journey Case Study.pptx
ADP Passwordless Journey Case Study.pptx
 
Generative AI Use Cases and Applications.pdf
Generative AI Use Cases and Applications.pdfGenerative AI Use Cases and Applications.pdf
Generative AI Use Cases and Applications.pdf
 
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptxHarnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
Harnessing Passkeys in the Battle Against AI-Powered Cyber Threats.pptx
 
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
Cyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptx
Cyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptxCyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptx
Cyber Insurance - RalphGilot - Embry-Riddle Aeronautical University.pptx
 
Oauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftOauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoft
 
JavaScript Usage Statistics 2024 - The Ultimate Guide
JavaScript Usage Statistics 2024 - The Ultimate GuideJavaScript Usage Statistics 2024 - The Ultimate Guide
JavaScript Usage Statistics 2024 - The Ultimate Guide
 
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
 
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
 
ERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage IntacctERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage Intacct
 
Microsoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - QuestionnaireMicrosoft CSP Briefing Pre-Engagement - Questionnaire
Microsoft CSP Briefing Pre-Engagement - Questionnaire
 
Design Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxDesign Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptx
 
ChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps ProductivityChatGPT and Beyond - Elevating DevOps Productivity
ChatGPT and Beyond - Elevating DevOps Productivity
 
WebAssembly is Key to Better LLM Performance
WebAssembly is Key to Better LLM PerformanceWebAssembly is Key to Better LLM Performance
WebAssembly is Key to Better LLM Performance
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe
 

Why your relationship is likely to last, or not: Local Interpretable Model-Agnostic Explanations