SlideShare a Scribd company logo
Using fairness metrics to
solve ethical dilemmas of
machine learning
Kovács László
laszlo@peak1014.com
Trust & Fairness
● Machine learning systems are not inherently fair
● Data requirements from the Probably Approximately Correct
learning theory: plenty of representative data
● Bias in → bias out
● Algorithms are objective, success criteria are not
Bias vs bias
The letter of the law
European Union: Policy and investment recommendations for trustworthy Artificial
Intelligence (guideline)
...
5. Measure and monitor the societal impact of AI
28. Consider the need for new regulation to ensure adequate protection from adverse impacts
12. Safeguard fundamental rights in AI-based public services and protect societal infrastructures
United States of America: Algorithmic Accountability Act of 2019
A bill to direct the Federal Trade Commission to require entities that use, store, or share personal
information to conduct automated decision system impact assessments (ADSIA). [... an ADSIA] means a
study evaluating an automated decision system and the automated decision system’s development process,
including the design and training data of the automated decision system, for impacts on accuracy, fairness,
bias, discrimination, privacy
The spirit of the law
Be fair, do not discriminate along sensitive attributes.
Be transparent, explainable, interpretable
What features, and by
what amount lead to the
prediction for a single
case?
What features, and by
what amount does the
model generally use to
make the predictions?
Explainability
(local scope)
Interpretability
(global scope)
Gaining the trust
of the user
Gaining the trust
of the analyst/regulator
This is not true.
This is not true.
The problem of fairness: error distribution
NegativePositive
Neg.
Pos. True Positive
False Negative
False Positive
True Negative
Reality
Prediction
Discrimination or unfairness:
systematic over- or underestimation for members of a group
Fairness metrics
NegativePositive
Neg.
Pos. True Positive
False Negative
False Positive
True Negative
Reality
Prediction
FalseTrue
False
True
Reality
Prediction
FalseTrue
False
True
Reality
Prediction
Group A Group B
Population
Fairness metrics: not just for sensitive decisions
COMPAS
COMPAS
A critique by ProPublica
A critique by ProPublica
Overall, Northpointe’s assessment tool correctly predicts recidivism 61
percent of the time. But blacks are almost twice as likely as whites to be
labeled a higher risk but not actually re-ofend. It makes the opposite
mistake among whites: They are much more likely than blacks to be
labeled lower risk but go on to commit other crimes.
Results from ProPublica
● They calculated the False Positive and False Negative rate
These are not the definition of the FPR/FNR!
Fairness metrics
NegativePositive
Neg.
Pos. True Positive
False Negative
False Positive
True Negative
Reality
Prediction
False Negatives
True Positives + False Negatives
False Negative Rate =
Among the people who turned out to recidivate,
how many did we mark as “unlikely to reofend”?
Fairness metrics
NegativePositive
Neg.
Pos. True Positive
False Negative
False Positive
True Negative
Reality
Prediction
False Positives
False Positives + True Negatives
False Positive Rate =
Among the people who turned out to be innocent,
how many did we mark as “likely to reofend”?
Fairness metrics
NegativePositive
Neg.
Pos. True Positive
False Negative
False Positive
True Negative
Reality
Prediction
True Positives
True Positives + False Positives
Precision =
Among the people who we marked as “likely to reofend”,
how many did actually do so?
Precision is also known as Positive Predictive Value.
Results from ProPublica
With proper False Discovery Rate (1–Precision) & False Omission Rate calculations:
>
<
<
>
● There was a mistake in the calculation.
● Can we have parity for all metrics?
The impossibility of fairness metrics
In real-life situations where
● the rate of positive cases in the
groups are not equal and
● the model is not perfect,
it is impossible to satisfy all of these:
False Negative
Rate Parity
False Positive Rate
Parity
Positive Predictive
Value (precision)
No One True Fairness Metric
● Feature importance and explainability are not enough
● Decide on the metric first, then do the analysis
● Cannot prove correctness, but can shed light on problems
● Aequitas Bias report
● AI Fairness 360 by IBM
Tools for calculating fairness
Pre-processing
What can I do?
Fair models Post-processing
Use models which are
using a penalty for
unfair behaviour
Transform features in a
way so that the new
features are not
correlated with the
sensitive variable
Use different thresholds
for the different groups
It’s a hard optimization
task, and some existing
models cannot be
modified.
The newly created
features will be
meaningless.
Only makes corrections
at the marginal cases.
Transparency can help
● Audit decision-making systems
● Do not store or use sensitive data
● Rethink contract strategy – some algorithms are proprietary
Thank you.
hello@peak1014.com
● Mountains under white mist at daytime by Ivana Cajina, https://unsplash.com/photos/HDd-NQ_AMNQ
● Overitting by Chabacano – Own work, CC BY-SA 4.0, https://commons.wikimedia.org/w/index.php?curid=3610704
● In an antique shop window by Pattie – https://www.flickr.com/photos/piratealice/3082374723
● Motorcycle wheel and tire by Oliver Walthard – https://unsplash.com/photos/mbL0XQy-d3o
● Woman wearing white and red blouse buying some veggies by Renate Vanaga – https://unsplash.com/photos/2pV2LwPVP9A
● Turned-on monitor by Blake Wisz – https://unsplash.com/photos/tE6th1h6Bfk
● https://worldvectorlogo.com/logo/the-washington-post, https://worldvectorlogo.com/logo/the-guardian-new-2018
● Shallow focus photo of compass by Aaron Burden – https://unsplash.com/photos/NXt5PrOb_7U
Image credits
Other Sources
● https://www.congress.gov/bill/116th-congress/house-bill/2231/text
● https://eur-lex.europa.eu/eli/reg/2016/679/oj
● https://www.theguardian.com/technology/2019/nov/10/apple-card-issuer-investigated-after-claims-of-sexist-credit-checks
● https://www.washingtonpost.com/health/2019/10/24/racial-bias-medical-algorithm-favors-white-patients-over-sicker-black-patients/
● https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
● Alexandra Chouldechova: Fair prediction with disparate impact: A study of bias in recidivism prediction instruments – https://arxiv.org/pdf/1610.07524.pdf

More Related Content

Similar to Using fairness metrics to solve ethical dilemmas of machine learning

Measures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairnessMeasures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairness
Manojit Nandi
 
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift Conference
 
Regoli fairness deep_learningitalia_20220127
Regoli fairness deep_learningitalia_20220127Regoli fairness deep_learningitalia_20220127
Regoli fairness deep_learningitalia_20220127
Matteo Testi
 
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...
Patrick Van Renterghem
 
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Richard Ingilby
 
Fraud analytics
Fraud analyticsFraud analytics
Fraud analytics
Simran Mondal
 
Algorithmic Bias: Challenges and Opportunities for AI in Healthcare
Algorithmic Bias:  Challenges and Opportunities for AI in HealthcareAlgorithmic Bias:  Challenges and Opportunities for AI in Healthcare
Algorithmic Bias: Challenges and Opportunities for AI in Healthcare
Gregory Nelson
 
Data Con LA 2022 - AI Ethics
Data Con LA 2022 - AI EthicsData Con LA 2022 - AI Ethics
Data Con LA 2022 - AI Ethics
Data Con LA
 
CommonAnalyticMistakes_v1.17_Unbranded
CommonAnalyticMistakes_v1.17_UnbrandedCommonAnalyticMistakes_v1.17_Unbranded
CommonAnalyticMistakes_v1.17_Unbranded
Jim Parnitzke
 
Module 4: Model Selection and Evaluation
Module 4: Model Selection and EvaluationModule 4: Model Selection and Evaluation
Module 4: Model Selection and Evaluation
Sara Hooker
 
What is fair when it comes to AI bias?
What is fair when it comes to AI bias?What is fair when it comes to AI bias?
What is fair when it comes to AI bias?
Strategy&, a member of the PwC network
 
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Krishnaram Kenthapadi
 
How ml can improve purchase conversions
How ml can improve purchase conversionsHow ml can improve purchase conversions
How ml can improve purchase conversions
Sudeep Shukla
 
When the AIs failures send us back to our own societal biases
When the AIs failures send us back to our own societal biasesWhen the AIs failures send us back to our own societal biases
When the AIs failures send us back to our own societal biases
Clément DUFFAU
 
Towards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptxTowards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptx
Luis775803
 
Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019
Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019
Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019
webwinkelvakdag
 
Make clinical prediction models great again
Make clinical prediction models great againMake clinical prediction models great again
Make clinical prediction models great again
BenVanCalster
 
IE_expressyourself_EssayH
IE_expressyourself_EssayHIE_expressyourself_EssayH
IE_expressyourself_EssayH
jk6653284
 
AI Developments and Trends (OECD)
AI Developments and Trends (OECD)AI Developments and Trends (OECD)
AI Developments and Trends (OECD)
AnandSRao1962
 
Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)
GoDataDriven
 

Similar to Using fairness metrics to solve ethical dilemmas of machine learning (20)

Measures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairnessMeasures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairness
 
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma...
 
Regoli fairness deep_learningitalia_20220127
Regoli fairness deep_learningitalia_20220127Regoli fairness deep_learningitalia_20220127
Regoli fairness deep_learningitalia_20220127
 
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...
 
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
Moving beyond multi-touch attribution - DigiMarCon CanWest 2024
 
Fraud analytics
Fraud analyticsFraud analytics
Fraud analytics
 
Algorithmic Bias: Challenges and Opportunities for AI in Healthcare
Algorithmic Bias:  Challenges and Opportunities for AI in HealthcareAlgorithmic Bias:  Challenges and Opportunities for AI in Healthcare
Algorithmic Bias: Challenges and Opportunities for AI in Healthcare
 
Data Con LA 2022 - AI Ethics
Data Con LA 2022 - AI EthicsData Con LA 2022 - AI Ethics
Data Con LA 2022 - AI Ethics
 
CommonAnalyticMistakes_v1.17_Unbranded
CommonAnalyticMistakes_v1.17_UnbrandedCommonAnalyticMistakes_v1.17_Unbranded
CommonAnalyticMistakes_v1.17_Unbranded
 
Module 4: Model Selection and Evaluation
Module 4: Model Selection and EvaluationModule 4: Model Selection and Evaluation
Module 4: Model Selection and Evaluation
 
What is fair when it comes to AI bias?
What is fair when it comes to AI bias?What is fair when it comes to AI bias?
What is fair when it comes to AI bias?
 
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)
 
How ml can improve purchase conversions
How ml can improve purchase conversionsHow ml can improve purchase conversions
How ml can improve purchase conversions
 
When the AIs failures send us back to our own societal biases
When the AIs failures send us back to our own societal biasesWhen the AIs failures send us back to our own societal biases
When the AIs failures send us back to our own societal biases
 
Towards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptxTowards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptx
 
Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019
Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019
Fairness in AI - Towards more Ethical predictive models - Big Data Expo 2019
 
Make clinical prediction models great again
Make clinical prediction models great againMake clinical prediction models great again
Make clinical prediction models great again
 
IE_expressyourself_EssayH
IE_expressyourself_EssayHIE_expressyourself_EssayH
IE_expressyourself_EssayH
 
AI Developments and Trends (OECD)
AI Developments and Trends (OECD)AI Developments and Trends (OECD)
AI Developments and Trends (OECD)
 
Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)Fairness in AI (DDSW 2019)
Fairness in AI (DDSW 2019)
 

Recently uploaded

STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
sameer shah
 
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
mkkikqvo
 
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdfUdemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Fernanda Palhano
 
A presentation that explain the Power BI Licensing
A presentation that explain the Power BI LicensingA presentation that explain the Power BI Licensing
A presentation that explain the Power BI Licensing
AlessioFois2
 
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens""Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
sameer shah
 
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
wyddcwye1
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Kiwi Creative
 
End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024
Lars Albertsson
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
roli9797
 
Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024
ElizabethGarrettChri
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
Bill641377
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
jitskeb
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
manishkhaire30
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
Social Samosa
 
writing report business partner b1+ .pdf
writing report business partner b1+ .pdfwriting report business partner b1+ .pdf
writing report business partner b1+ .pdf
VyNguyen709676
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
nyfuhyz
 
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
ihavuls
 
Build applications with generative AI on Google Cloud
Build applications with generative AI on Google CloudBuild applications with generative AI on Google Cloud
Build applications with generative AI on Google Cloud
Márton Kodok
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
nuttdpt
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
aqzctr7x
 

Recently uploaded (20)

STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
STATATHON: Unleashing the Power of Statistics in a 48-Hour Knowledge Extravag...
 
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
原版一比一多伦多大学毕业证(UofT毕业证书)如何办理
 
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdfUdemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
Udemy_2024_Global_Learning_Skills_Trends_Report (1).pdf
 
A presentation that explain the Power BI Licensing
A presentation that explain the Power BI LicensingA presentation that explain the Power BI Licensing
A presentation that explain the Power BI Licensing
 
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens""Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
"Financial Odyssey: Navigating Past Performance Through Diverse Analytical Lens"
 
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
原版一比一利兹贝克特大学毕业证(LeedsBeckett毕业证书)如何办理
 
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging DataPredictably Improve Your B2B Tech Company's Performance by Leveraging Data
Predictably Improve Your B2B Tech Company's Performance by Leveraging Data
 
End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024End-to-end pipeline agility - Berlin Buzzwords 2024
End-to-end pipeline agility - Berlin Buzzwords 2024
 
Analysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performanceAnalysis insight about a Flyball dog competition team's performance
Analysis insight about a Flyball dog competition team's performance
 
Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024Open Source Contributions to Postgres: The Basics POSETTE 2024
Open Source Contributions to Postgres: The Basics POSETTE 2024
 
Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...Population Growth in Bataan: The effects of population growth around rural pl...
Population Growth in Bataan: The effects of population growth around rural pl...
 
Experts live - Improving user adoption with AI
Experts live - Improving user adoption with AIExperts live - Improving user adoption with AI
Experts live - Improving user adoption with AI
 
Learn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queriesLearn SQL from basic queries to Advance queries
Learn SQL from basic queries to Advance queries
 
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
4th Modern Marketing Reckoner by MMA Global India & Group M: 60+ experts on W...
 
writing report business partner b1+ .pdf
writing report business partner b1+ .pdfwriting report business partner b1+ .pdf
writing report business partner b1+ .pdf
 
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
一比一原版(UMN文凭证书)明尼苏达大学毕业证如何办理
 
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
原版制作(unimelb毕业证书)墨尔本大学毕业证Offer一模一样
 
Build applications with generative AI on Google Cloud
Build applications with generative AI on Google CloudBuild applications with generative AI on Google Cloud
Build applications with generative AI on Google Cloud
 
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
一比一原版(UCSB文凭证书)圣芭芭拉分校毕业证如何办理
 
一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理一比一原版(UO毕业证)渥太华大学毕业证如何办理
一比一原版(UO毕业证)渥太华大学毕业证如何办理
 

Using fairness metrics to solve ethical dilemmas of machine learning

  • 1. Using fairness metrics to solve ethical dilemmas of machine learning Kovács László laszlo@peak1014.com
  • 2.
  • 3. Trust & Fairness ● Machine learning systems are not inherently fair ● Data requirements from the Probably Approximately Correct learning theory: plenty of representative data ● Bias in → bias out ● Algorithms are objective, success criteria are not
  • 5. The letter of the law European Union: Policy and investment recommendations for trustworthy Artificial Intelligence (guideline) ... 5. Measure and monitor the societal impact of AI 28. Consider the need for new regulation to ensure adequate protection from adverse impacts 12. Safeguard fundamental rights in AI-based public services and protect societal infrastructures United States of America: Algorithmic Accountability Act of 2019 A bill to direct the Federal Trade Commission to require entities that use, store, or share personal information to conduct automated decision system impact assessments (ADSIA). [... an ADSIA] means a study evaluating an automated decision system and the automated decision system’s development process, including the design and training data of the automated decision system, for impacts on accuracy, fairness, bias, discrimination, privacy
  • 6. The spirit of the law Be fair, do not discriminate along sensitive attributes. Be transparent, explainable, interpretable
  • 7. What features, and by what amount lead to the prediction for a single case? What features, and by what amount does the model generally use to make the predictions? Explainability (local scope) Interpretability (global scope) Gaining the trust of the user Gaining the trust of the analyst/regulator
  • 8. This is not true.
  • 9. This is not true.
  • 10. The problem of fairness: error distribution NegativePositive Neg. Pos. True Positive False Negative False Positive True Negative Reality Prediction Discrimination or unfairness: systematic over- or underestimation for members of a group
  • 11. Fairness metrics NegativePositive Neg. Pos. True Positive False Negative False Positive True Negative Reality Prediction FalseTrue False True Reality Prediction FalseTrue False True Reality Prediction Group A Group B Population
  • 12. Fairness metrics: not just for sensitive decisions
  • 15. A critique by ProPublica
  • 16. A critique by ProPublica Overall, Northpointe’s assessment tool correctly predicts recidivism 61 percent of the time. But blacks are almost twice as likely as whites to be labeled a higher risk but not actually re-ofend. It makes the opposite mistake among whites: They are much more likely than blacks to be labeled lower risk but go on to commit other crimes.
  • 17. Results from ProPublica ● They calculated the False Positive and False Negative rate These are not the definition of the FPR/FNR!
  • 18. Fairness metrics NegativePositive Neg. Pos. True Positive False Negative False Positive True Negative Reality Prediction False Negatives True Positives + False Negatives False Negative Rate = Among the people who turned out to recidivate, how many did we mark as “unlikely to reofend”?
  • 19. Fairness metrics NegativePositive Neg. Pos. True Positive False Negative False Positive True Negative Reality Prediction False Positives False Positives + True Negatives False Positive Rate = Among the people who turned out to be innocent, how many did we mark as “likely to reofend”?
  • 20. Fairness metrics NegativePositive Neg. Pos. True Positive False Negative False Positive True Negative Reality Prediction True Positives True Positives + False Positives Precision = Among the people who we marked as “likely to reofend”, how many did actually do so? Precision is also known as Positive Predictive Value.
  • 21. Results from ProPublica With proper False Discovery Rate (1–Precision) & False Omission Rate calculations: > < < >
  • 22. ● There was a mistake in the calculation. ● Can we have parity for all metrics?
  • 23. The impossibility of fairness metrics In real-life situations where ● the rate of positive cases in the groups are not equal and ● the model is not perfect, it is impossible to satisfy all of these: False Negative Rate Parity False Positive Rate Parity Positive Predictive Value (precision)
  • 24. No One True Fairness Metric ● Feature importance and explainability are not enough ● Decide on the metric first, then do the analysis ● Cannot prove correctness, but can shed light on problems
  • 25. ● Aequitas Bias report ● AI Fairness 360 by IBM Tools for calculating fairness
  • 26. Pre-processing What can I do? Fair models Post-processing Use models which are using a penalty for unfair behaviour Transform features in a way so that the new features are not correlated with the sensitive variable Use different thresholds for the different groups It’s a hard optimization task, and some existing models cannot be modified. The newly created features will be meaningless. Only makes corrections at the marginal cases.
  • 27. Transparency can help ● Audit decision-making systems ● Do not store or use sensitive data ● Rethink contract strategy – some algorithms are proprietary
  • 29. ● Mountains under white mist at daytime by Ivana Cajina, https://unsplash.com/photos/HDd-NQ_AMNQ ● Overitting by Chabacano – Own work, CC BY-SA 4.0, https://commons.wikimedia.org/w/index.php?curid=3610704 ● In an antique shop window by Pattie – https://www.flickr.com/photos/piratealice/3082374723 ● Motorcycle wheel and tire by Oliver Walthard – https://unsplash.com/photos/mbL0XQy-d3o ● Woman wearing white and red blouse buying some veggies by Renate Vanaga – https://unsplash.com/photos/2pV2LwPVP9A ● Turned-on monitor by Blake Wisz – https://unsplash.com/photos/tE6th1h6Bfk ● https://worldvectorlogo.com/logo/the-washington-post, https://worldvectorlogo.com/logo/the-guardian-new-2018 ● Shallow focus photo of compass by Aaron Burden – https://unsplash.com/photos/NXt5PrOb_7U Image credits
  • 30. Other Sources ● https://www.congress.gov/bill/116th-congress/house-bill/2231/text ● https://eur-lex.europa.eu/eli/reg/2016/679/oj ● https://www.theguardian.com/technology/2019/nov/10/apple-card-issuer-investigated-after-claims-of-sexist-credit-checks ● https://www.washingtonpost.com/health/2019/10/24/racial-bias-medical-algorithm-favors-white-patients-over-sicker-black-patients/ ● https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing ● Alexandra Chouldechova: Fair prediction with disparate impact: A study of bias in recidivism prediction instruments – https://arxiv.org/pdf/1610.07524.pdf