SlideShare a Scribd company logo
1 of 15
Download to read offline
Algorithmic Fairness
Navdeep Sharma
Data & AI Architect - Accenture, The Dock
Shift AI
Algorithmic Bias: Why
is it important?
Set the scene: Fairness
Definitions
Introduction to
Fairness Metrics
Introduction to
Accenture Fairness Tool
0201
03 04Agenda
Our society's growing reliance on algorithmic decision making,
particularly in social and economic areas has raised a concern; that they
may inadvertently discriminate against certain groups.
“Business needs to consider
society as a stakeholder.” -
Cennydd Bowles, Future Ethics
Introduction | Context
Objective decision-making is a challenge.
“Algorithmic Fairness is a practice that
aims to mitigate unconscious bias against
any individual or group of people in
Machine Learning.”
“Data biases are inevitable. We must
design algorithms that account for
them. "
“The model summarizes the data correctly. If
the data is biased it is not the algorithm’s
fault.”
VS
From “Tutorial: 21 fairness definitions and their politics” on YouTube
From “Tutorial: 21 fairness definitions and their politics” on YouTube
Reference :
https://www.theverge.com/2018/1/12/16882408/google-racist-gorillas-photo-recognition-algorithm-ai
https://www.theverge.com/2018/10/10/17958784/ai-recruiting-tool-bias-amazon-report
Definitions:
“The Treaty on the Functioning of the European Union
prohibits (TFEU) discrimination on grounds of nationality.
It also encourages to combat discrimination based on
sex, racial or ethnic origin, religion or belief, disability,
age or sexual orientation.”
Status Definition: Privileged vs Unprivileged
Example: In criminal risk assessment tools, a common
example of protected feature is race, with the designated
levels: white defendants – privileged group vs black
defendants – unprivileged.
Group Bias VS Individual Bias:Protected feature:
“Group fairness approaches partition the
population/sample into groups and seeks to equalize a
statistical measure across the groups. ”
“Individual fairness seeks to understand if similar
individuals are treated similarly irrespective of their
membership to any of the groups.”
Mutual Information
Identifies proxies for protected feature
Prevalence Analysis
Fraction of a population that satisfies a
given outcome
Disparate Impact
Quantifies disparity of outcomes for
different protected groups
Predictive Parity - False Positive Rates
Proportion of all negatives that still yield positive test
outcomes
Predictive Parity - True Positive
Rates
Predictive Parity - Positive
Predictive Power
Predictive Parity - FalseNegative
Rates
7
Metrics Introduction
Myriad of metrics: which one to choose?
Individualfairness
…
“Tutorial: 21 fairness definitions and their politics” on YouTube
Mutual Information
Approach: Quantifies the amount of information obtained
about one random variable through observing the other
random variable.
Mutual Information for a Protected Variable, assesses the
relationship between the protected and unprotected
variables (which could be used in the model build as proxies
for sensitive ones and generate bias).
Objectives:
• Identify proxies
• Provoke further analysis:
• Is ‘blindness’ w.r.t. protected feature enough?
• Predictive power of the proxies with respect to targeted model
Prevalence
Approach: The prevalence of a certain outcome
in a certain population can be defined as the
fraction of that population that satisfies a given
outcome, say Y = reoffended. In other words
Prevalence Ratio for a given protected variable is
defined as the ratio of the prevalence in the
privileged population to the prevalence in the
unprivileged group. Prevalence Ratio is calculated
on the ground truth. For example:
Prevalence ratio (White vs Black) =
!"#
!$$%
%!&"
'(&"
= 34%
Disparate Impact
TN= 2812 FP = 189
FN = 677 TP = 681
Black Total Pop = 4359
Recidivated
Predicted: low risk Predicted: high risk
Approach: Unintentional bias is encoded via disparate
impact, which occurs when a selection process has
widely different outcomes for different groups, even as
it appears to be neutral.
Calculation:
Disparate Impact for a protected variable is the ratio of
the % privileged population with a predicted outcome
to the % unprivileged population with a predicted
outcome.
US Law:
Originally, the Uniform Guidelines on Employee Selection Procedures provided a simple "80
percent" rule for determining that a company's selection system was having an "adverse
impact" on a minority group.
Cautionary points: “Courts in the U.S. have questioned the arbitrary nature of the 80 percent rule”
TN = 1886 FP = 26
FN = 147 TP = 94
Didnotrecidivate
Recidivated
Predicted: low risk Predicted: high risk
Didnot
recidivate
White Total Pop = 2154
DI = 0.06/0.2=30%
(189+681)/
4358 =
0.20
(26+94)/
2154 =
0.06
False Positive Rate (FPR)
TN= 2812 FP = 189
FN = 677 TP = 681
Black Total Pop = 4,359
Recidivated
Predicted: low risk Predicted: high risk
Approach: Parity for False Positive Rates (FPR) implies that
the false positive rates are equal among the privileged and
unprivileged population.
Calculation:
Error Ratio for a given protected variable, is defined as
the ratio of error in the privileged population to the
ratio of error in the unprivileged population
Legislation: No legal precedent for error ratio, however
a similar approach to DI can be applied by using the
80% rule (bias when ratio of rates <= 0.8)
Didnotrecidivate
Recidivated
Predicted: low risk Predicted: high risk
Didnotrecidivate
White Total Pop = 2,154
TN= 1886 FP = 26
FN = 147 TP = 94
189/(2812 +
189) = 0.063
26/(2154 +
26) = 0.013
Error Ratio = 0.013/0.063 = 0.21
There is now a consensus amongst academia and scientists that
algorithmic fairness can not be achieved by the application of data
science alone.
The complexity of choosing the right solution to allow for group and for
individual fairness for example, or to account for accuracy versus
fairness, or the complexities that come with scale, and many more is a
challenge in itself.
All of this is further compounded by myriad of non science factors: What
may be fair statistically quite often can fall short ethically or may not be
viable from a business perspective.
"Bias is a feature of statistical
models. Fairness is a feature of
human value judgments.”
Learnings
https://www.semanticscholar.org/paper/Fairness-aware-machine-learning%3A-a-perspective-
Žliobaitė/69c7bf934e9ac7673be590f7656bcb38fcb9da48
What are main general challenges we have encountered when
assessing real-life use cases for potential bias?
• Metric selection
• Academic – Industry gap
• Non-binary Protected feature
• More than one protected feature
• Legislation and guidelines
Data scientists can solve for many fairness problems
from a technical perspective by using statistical
metrics but this is not just a data science problem, it
requires input from the broader organisation.
The tool starts with the data scientist and is
integrated with Jupyter hub. We want to add
fairness as a step into the current data science
workflow. Analyses are pushed to a repository for
business users.
The business user can explore the interactive
analyses and embed them in reports for
dissemination for the broader business for decision
making. As a communication tool it facilitates a
deeper understanding of the challenge.
How does the tool work?
Accenture Fairness Tool
Thank You.
Navdeep Sharma
navdeep.a.sharma@accenture.com

More Related Content

What's hot

Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...
Krishnaram Kenthapadi
 
The AI Index 2023 Annual Report by Stanford University.pdf
The AI Index 2023 Annual Report by Stanford University.pdfThe AI Index 2023 Annual Report by Stanford University.pdf
The AI Index 2023 Annual Report by Stanford University.pdf
AI Geek (wishesh)
 
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
Edge AI and Vision Alliance
 
Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)
Krishnaram Kenthapadi
 

What's hot (20)

Introduction to LLMs
Introduction to LLMsIntroduction to LLMs
Introduction to LLMs
 
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
Uncertainty Quantification with Unsupervised Deep learning and Multi Agent Sy...
 
Responsible Data Use in AI - core tech pillars
Responsible Data Use in AI - core tech pillarsResponsible Data Use in AI - core tech pillars
Responsible Data Use in AI - core tech pillars
 
Responsible AI
Responsible AIResponsible AI
Responsible AI
 
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (WS...
 
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...
 
Naive Bayes Classifier
Naive Bayes ClassifierNaive Bayes Classifier
Naive Bayes Classifier
 
The AI Index 2023 Annual Report by Stanford University.pdf
The AI Index 2023 Annual Report by Stanford University.pdfThe AI Index 2023 Annual Report by Stanford University.pdf
The AI Index 2023 Annual Report by Stanford University.pdf
 
Algorithmic Bias - What is it? Why should we care? What can we do about it?
Algorithmic Bias - What is it? Why should we care? What can we do about it? Algorithmic Bias - What is it? Why should we care? What can we do about it?
Algorithmic Bias - What is it? Why should we care? What can we do about it?
 
Community detection in social networks
Community detection in social networksCommunity detection in social networks
Community detection in social networks
 
Multiclass classification of imbalanced data
Multiclass classification of imbalanced dataMulticlass classification of imbalanced data
Multiclass classification of imbalanced data
 
Naive bayes
Naive bayesNaive bayes
Naive bayes
 
Use Case Patterns for LLM Applications (1).pdf
Use Case Patterns for LLM Applications (1).pdfUse Case Patterns for LLM Applications (1).pdf
Use Case Patterns for LLM Applications (1).pdf
 
03 Ego Network Analysis (2016)
03 Ego Network Analysis (2016)03 Ego Network Analysis (2016)
03 Ego Network Analysis (2016)
 
Cavalry Ventures | Deep Dive: Generative AI
Cavalry Ventures | Deep Dive: Generative AICavalry Ventures | Deep Dive: Generative AI
Cavalry Ventures | Deep Dive: Generative AI
 
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
 
Ethical Issues in Machine Learning Algorithms. (Part 1)
Ethical Issues in Machine Learning Algorithms. (Part 1)Ethical Issues in Machine Learning Algorithms. (Part 1)
Ethical Issues in Machine Learning Algorithms. (Part 1)
 
Responsible AI
Responsible AIResponsible AI
Responsible AI
 
Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)Explainable AI in Industry (AAAI 2020 Tutorial)
Explainable AI in Industry (AAAI 2020 Tutorial)
 
AI in Bioinformatics
AI in BioinformaticsAI in Bioinformatics
AI in Bioinformatics
 

Similar to Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma (Accenture)

Data Mining - Health Insurance - Jabran Noor
Data Mining - Health Insurance - Jabran NoorData Mining - Health Insurance - Jabran Noor
Data Mining - Health Insurance - Jabran Noor
Jabran Noor
 
Predictive analytics-white-paper
Predictive analytics-white-paperPredictive analytics-white-paper
Predictive analytics-white-paper
Shubhashish Biswas
 
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
 

Similar to Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma (Accenture) (20)

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
 
AI Developments and Trends (OECD)
AI Developments and Trends (OECD)AI Developments and Trends (OECD)
AI Developments and Trends (OECD)
 
ANIn Kolkata April 2024 |Ethics of AI by Abhishek Nandy
ANIn Kolkata April 2024 |Ethics of AI by Abhishek NandyANIn Kolkata April 2024 |Ethics of AI by Abhishek Nandy
ANIn Kolkata April 2024 |Ethics of AI by Abhishek Nandy
 
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?
 
Measures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairnessMeasures and mismeasures of algorithmic fairness
Measures and mismeasures of algorithmic fairness
 
Using fairness metrics to solve ethical dilemmas of machine learning
Using fairness metrics to solve ethical dilemmas of machine learningUsing fairness metrics to solve ethical dilemmas of machine learning
Using fairness metrics to solve ethical dilemmas of machine learning
 
Regoli fairness deep_learningitalia_20220127
Regoli fairness deep_learningitalia_20220127Regoli fairness deep_learningitalia_20220127
Regoli fairness deep_learningitalia_20220127
 
Detecting health insurance fraud using analytics
Detecting health insurance fraud using analytics Detecting health insurance fraud using analytics
Detecting health insurance fraud using analytics
 
Data Mining - Health Insurance - Jabran Noor
Data Mining - Health Insurance - Jabran NoorData Mining - Health Insurance - Jabran Noor
Data Mining - Health Insurance - Jabran Noor
 
Fairness and Bias in Machine Learning
Fairness and Bias in Machine LearningFairness and Bias in Machine Learning
Fairness and Bias in Machine Learning
 
AI Governance and Ethics - Industry Standards
AI Governance and Ethics - Industry StandardsAI Governance and Ethics - Industry Standards
AI Governance and Ethics - Industry Standards
 
Responsible AI in Industry: Practical Challenges and Lessons Learned
Responsible AI in Industry: Practical Challenges and Lessons LearnedResponsible AI in Industry: Practical Challenges and Lessons Learned
Responsible AI in Industry: Practical Challenges and Lessons Learned
 
Predictive analytics-white-paper
Predictive analytics-white-paperPredictive analytics-white-paper
Predictive analytics-white-paper
 
Industry Standards as vehicle to address socio-technical AI challenges
Industry Standards as vehicle to address socio-technical AI challengesIndustry Standards as vehicle to address socio-technical AI challenges
Industry Standards as vehicle to address socio-technical AI challenges
 
Human Agency on Algorithmic Systems
Human Agency on Algorithmic SystemsHuman Agency on Algorithmic Systems
Human Agency on Algorithmic Systems
 
Towards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptxTowards Responsible AI - NY.pptx
Towards Responsible AI - NY.pptx
 
Bsa cpd a_koene2016
Bsa cpd a_koene2016Bsa cpd a_koene2016
Bsa cpd a_koene2016
 
Towards Responsible AI - Global AI Student Conference 2022.pptx
Towards Responsible AI - Global AI Student Conference 2022.pptxTowards Responsible AI - Global AI Student Conference 2022.pptx
Towards Responsible AI - Global AI Student Conference 2022.pptx
 
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)
 

More from Shift Conference

More from Shift Conference (20)

Shift Remote: AI: How Does Face Recognition Work (ars futura)
Shift Remote: AI: How Does Face Recognition Work  (ars futura)Shift Remote: AI: How Does Face Recognition Work  (ars futura)
Shift Remote: AI: How Does Face Recognition Work (ars futura)
 
Shift Remote: AI: Behind the scenes development in an AI company - Matija Ili...
Shift Remote: AI: Behind the scenes development in an AI company - Matija Ili...Shift Remote: AI: Behind the scenes development in an AI company - Matija Ili...
Shift Remote: AI: Behind the scenes development in an AI company - Matija Ili...
 
Shift Remote: AI: Smarter AI with analytical graph databases - Victor Lee (Ti...
Shift Remote: AI: Smarter AI with analytical graph databases - Victor Lee (Ti...Shift Remote: AI: Smarter AI with analytical graph databases - Victor Lee (Ti...
Shift Remote: AI: Smarter AI with analytical graph databases - Victor Lee (Ti...
 
Shift Remote: DevOps: Devops with Azure Devops and Github - Juarez Junior (Mi...
Shift Remote: DevOps: Devops with Azure Devops and Github - Juarez Junior (Mi...Shift Remote: DevOps: Devops with Azure Devops and Github - Juarez Junior (Mi...
Shift Remote: DevOps: Devops with Azure Devops and Github - Juarez Junior (Mi...
 
Shift Remote: DevOps: Autodesks research into digital twins for AEC - Kean W...
Shift Remote: DevOps: Autodesks research into digital twins for AEC -  Kean W...Shift Remote: DevOps: Autodesks research into digital twins for AEC -  Kean W...
Shift Remote: DevOps: Autodesks research into digital twins for AEC - Kean W...
 
Shift Remote: DevOps: When metrics are not enough, and everyone is on-call - ...
Shift Remote: DevOps: When metrics are not enough, and everyone is on-call - ...Shift Remote: DevOps: When metrics are not enough, and everyone is on-call - ...
Shift Remote: DevOps: When metrics are not enough, and everyone is on-call - ...
 
Shift Remote: DevOps: Modern incident management with opsgenie - Kristijan L...
Shift Remote: DevOps: Modern incident management with opsgenie -  Kristijan L...Shift Remote: DevOps: Modern incident management with opsgenie -  Kristijan L...
Shift Remote: DevOps: Modern incident management with opsgenie - Kristijan L...
 
Shift Remote: DevOps: Gitlab ci hands-on experience - Ivan Rimac (Barrage)
Shift Remote: DevOps: Gitlab ci hands-on experience - Ivan Rimac (Barrage)Shift Remote: DevOps: Gitlab ci hands-on experience - Ivan Rimac (Barrage)
Shift Remote: DevOps: Gitlab ci hands-on experience - Ivan Rimac (Barrage)
 
Shift Remote: DevOps: DevOps Heroes - Adding Advanced Automation to your Tool...
Shift Remote: DevOps: DevOps Heroes - Adding Advanced Automation to your Tool...Shift Remote: DevOps: DevOps Heroes - Adding Advanced Automation to your Tool...
Shift Remote: DevOps: DevOps Heroes - Adding Advanced Automation to your Tool...
 
Shift Remote: DevOps: An (Un)expected Journey - Zeljko Margeta (RBA)
Shift Remote: DevOps: An (Un)expected Journey - Zeljko Margeta (RBA)Shift Remote: DevOps: An (Un)expected Journey - Zeljko Margeta (RBA)
Shift Remote: DevOps: An (Un)expected Journey - Zeljko Margeta (RBA)
 
Shift Remote: Game Dev - Localising Mobile Games - Marta Kunic (Nanobit)
Shift Remote: Game Dev - Localising Mobile Games - Marta Kunic (Nanobit)Shift Remote: Game Dev - Localising Mobile Games - Marta Kunic (Nanobit)
Shift Remote: Game Dev - Localising Mobile Games - Marta Kunic (Nanobit)
 
Shift Remote: Game Dev - Challenges Introducing Open Source to the Games Indu...
Shift Remote: Game Dev - Challenges Introducing Open Source to the Games Indu...Shift Remote: Game Dev - Challenges Introducing Open Source to the Games Indu...
Shift Remote: Game Dev - Challenges Introducing Open Source to the Games Indu...
 
Shift Remote: Game Dev - Ghost in the Machine: Authorial Voice in System Desi...
Shift Remote: Game Dev - Ghost in the Machine: Authorial Voice in System Desi...Shift Remote: Game Dev - Ghost in the Machine: Authorial Voice in System Desi...
Shift Remote: Game Dev - Ghost in the Machine: Authorial Voice in System Desi...
 
Shift Remote: Game Dev - Building Better Worlds with Game Culturalization - K...
Shift Remote: Game Dev - Building Better Worlds with Game Culturalization - K...Shift Remote: Game Dev - Building Better Worlds with Game Culturalization - K...
Shift Remote: Game Dev - Building Better Worlds with Game Culturalization - K...
 
Shift Remote: Game Dev - Open Match: An Open Source Matchmaking Framework - J...
Shift Remote: Game Dev - Open Match: An Open Source Matchmaking Framework - J...Shift Remote: Game Dev - Open Match: An Open Source Matchmaking Framework - J...
Shift Remote: Game Dev - Open Match: An Open Source Matchmaking Framework - J...
 
Shift Remote: Game Dev - Designing Inside the Box - Fernando Reyes Medina (34...
Shift Remote: Game Dev - Designing Inside the Box - Fernando Reyes Medina (34...Shift Remote: Game Dev - Designing Inside the Box - Fernando Reyes Medina (34...
Shift Remote: Game Dev - Designing Inside the Box - Fernando Reyes Medina (34...
 
Shift Remote: Mobile - Efficiently Building Native Frameworks for Multiple Pl...
Shift Remote: Mobile - Efficiently Building Native Frameworks for Multiple Pl...Shift Remote: Mobile - Efficiently Building Native Frameworks for Multiple Pl...
Shift Remote: Mobile - Efficiently Building Native Frameworks for Multiple Pl...
 
Shift Remote: Mobile - Introduction to MotionLayout on Android - Denis Fodor ...
Shift Remote: Mobile - Introduction to MotionLayout on Android - Denis Fodor ...Shift Remote: Mobile - Introduction to MotionLayout on Android - Denis Fodor ...
Shift Remote: Mobile - Introduction to MotionLayout on Android - Denis Fodor ...
 
Shift Remote: Mobile - Devops-ify your life with Github Actions - Nicola Cort...
Shift Remote: Mobile - Devops-ify your life with Github Actions - Nicola Cort...Shift Remote: Mobile - Devops-ify your life with Github Actions - Nicola Cort...
Shift Remote: Mobile - Devops-ify your life with Github Actions - Nicola Cort...
 
Shift Remote: WEB - GraphQL and React – Quick Start - Dubravko Bogovic (Infobip)
Shift Remote: WEB - GraphQL and React – Quick Start - Dubravko Bogovic (Infobip)Shift Remote: WEB - GraphQL and React – Quick Start - Dubravko Bogovic (Infobip)
Shift Remote: WEB - GraphQL and React – Quick Start - Dubravko Bogovic (Infobip)
 

Recently uploaded

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
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
 

Recently uploaded (20)

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
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
 
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
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
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 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...
 
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
 
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
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
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
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
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
 
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...
 
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
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 

Shift AI 2020: How to identify and treat biases in ML Models | Navdeep Sharma (Accenture)

  • 1. Algorithmic Fairness Navdeep Sharma Data & AI Architect - Accenture, The Dock Shift AI
  • 2. Algorithmic Bias: Why is it important? Set the scene: Fairness Definitions Introduction to Fairness Metrics Introduction to Accenture Fairness Tool 0201 03 04Agenda
  • 3. Our society's growing reliance on algorithmic decision making, particularly in social and economic areas has raised a concern; that they may inadvertently discriminate against certain groups. “Business needs to consider society as a stakeholder.” - Cennydd Bowles, Future Ethics Introduction | Context Objective decision-making is a challenge. “Algorithmic Fairness is a practice that aims to mitigate unconscious bias against any individual or group of people in Machine Learning.”
  • 4. “Data biases are inevitable. We must design algorithms that account for them. " “The model summarizes the data correctly. If the data is biased it is not the algorithm’s fault.” VS From “Tutorial: 21 fairness definitions and their politics” on YouTube From “Tutorial: 21 fairness definitions and their politics” on YouTube
  • 6. Definitions: “The Treaty on the Functioning of the European Union prohibits (TFEU) discrimination on grounds of nationality. It also encourages to combat discrimination based on sex, racial or ethnic origin, religion or belief, disability, age or sexual orientation.” Status Definition: Privileged vs Unprivileged Example: In criminal risk assessment tools, a common example of protected feature is race, with the designated levels: white defendants – privileged group vs black defendants – unprivileged. Group Bias VS Individual Bias:Protected feature: “Group fairness approaches partition the population/sample into groups and seeks to equalize a statistical measure across the groups. ” “Individual fairness seeks to understand if similar individuals are treated similarly irrespective of their membership to any of the groups.”
  • 7. Mutual Information Identifies proxies for protected feature Prevalence Analysis Fraction of a population that satisfies a given outcome Disparate Impact Quantifies disparity of outcomes for different protected groups Predictive Parity - False Positive Rates Proportion of all negatives that still yield positive test outcomes Predictive Parity - True Positive Rates Predictive Parity - Positive Predictive Power Predictive Parity - FalseNegative Rates 7 Metrics Introduction Myriad of metrics: which one to choose? Individualfairness … “Tutorial: 21 fairness definitions and their politics” on YouTube
  • 8. Mutual Information Approach: Quantifies the amount of information obtained about one random variable through observing the other random variable. Mutual Information for a Protected Variable, assesses the relationship between the protected and unprotected variables (which could be used in the model build as proxies for sensitive ones and generate bias). Objectives: • Identify proxies • Provoke further analysis: • Is ‘blindness’ w.r.t. protected feature enough? • Predictive power of the proxies with respect to targeted model
  • 9. Prevalence Approach: The prevalence of a certain outcome in a certain population can be defined as the fraction of that population that satisfies a given outcome, say Y = reoffended. In other words Prevalence Ratio for a given protected variable is defined as the ratio of the prevalence in the privileged population to the prevalence in the unprivileged group. Prevalence Ratio is calculated on the ground truth. For example: Prevalence ratio (White vs Black) = !"# !$$% %!&" '(&" = 34%
  • 10. Disparate Impact TN= 2812 FP = 189 FN = 677 TP = 681 Black Total Pop = 4359 Recidivated Predicted: low risk Predicted: high risk Approach: Unintentional bias is encoded via disparate impact, which occurs when a selection process has widely different outcomes for different groups, even as it appears to be neutral. Calculation: Disparate Impact for a protected variable is the ratio of the % privileged population with a predicted outcome to the % unprivileged population with a predicted outcome. US Law: Originally, the Uniform Guidelines on Employee Selection Procedures provided a simple "80 percent" rule for determining that a company's selection system was having an "adverse impact" on a minority group. Cautionary points: “Courts in the U.S. have questioned the arbitrary nature of the 80 percent rule” TN = 1886 FP = 26 FN = 147 TP = 94 Didnotrecidivate Recidivated Predicted: low risk Predicted: high risk Didnot recidivate White Total Pop = 2154 DI = 0.06/0.2=30% (189+681)/ 4358 = 0.20 (26+94)/ 2154 = 0.06
  • 11. False Positive Rate (FPR) TN= 2812 FP = 189 FN = 677 TP = 681 Black Total Pop = 4,359 Recidivated Predicted: low risk Predicted: high risk Approach: Parity for False Positive Rates (FPR) implies that the false positive rates are equal among the privileged and unprivileged population. Calculation: Error Ratio for a given protected variable, is defined as the ratio of error in the privileged population to the ratio of error in the unprivileged population Legislation: No legal precedent for error ratio, however a similar approach to DI can be applied by using the 80% rule (bias when ratio of rates <= 0.8) Didnotrecidivate Recidivated Predicted: low risk Predicted: high risk Didnotrecidivate White Total Pop = 2,154 TN= 1886 FP = 26 FN = 147 TP = 94 189/(2812 + 189) = 0.063 26/(2154 + 26) = 0.013 Error Ratio = 0.013/0.063 = 0.21
  • 12. There is now a consensus amongst academia and scientists that algorithmic fairness can not be achieved by the application of data science alone. The complexity of choosing the right solution to allow for group and for individual fairness for example, or to account for accuracy versus fairness, or the complexities that come with scale, and many more is a challenge in itself. All of this is further compounded by myriad of non science factors: What may be fair statistically quite often can fall short ethically or may not be viable from a business perspective. "Bias is a feature of statistical models. Fairness is a feature of human value judgments.” Learnings https://www.semanticscholar.org/paper/Fairness-aware-machine-learning%3A-a-perspective- Žliobaitė/69c7bf934e9ac7673be590f7656bcb38fcb9da48
  • 13. What are main general challenges we have encountered when assessing real-life use cases for potential bias? • Metric selection • Academic – Industry gap • Non-binary Protected feature • More than one protected feature • Legislation and guidelines
  • 14. Data scientists can solve for many fairness problems from a technical perspective by using statistical metrics but this is not just a data science problem, it requires input from the broader organisation. The tool starts with the data scientist and is integrated with Jupyter hub. We want to add fairness as a step into the current data science workflow. Analyses are pushed to a repository for business users. The business user can explore the interactive analyses and embed them in reports for dissemination for the broader business for decision making. As a communication tool it facilitates a deeper understanding of the challenge. How does the tool work? Accenture Fairness Tool