SlideShare una empresa de Scribd logo
1 de 32
October 2020 : DCLA 2020
Using AI to Build Fair and
Equitable Workplaces
Sonya Balzer
Dr. Lawrence Spracklen
RSquared.AI
Today’s Speakers
Sonya Balzer
Director of Marketing, RSquared
Marketing Director, SupportLogic
Dr. Lawrence Spracklen
CTO, RSquared
VP of Engineering & Data Science, SupportLogic
VP of Engineering, Alpine Data
VP of Engineering, Ayasdi
Where We’re From
• RSquared is a data-driven actionable insights
platform used by organizations to improve
workplace culture, inclusion and productivity
• Using AI / NLP to securely analyze employee
interactions and attitudes through work emails,
chats, and other digital communications
The Current Environment
+ +
Equality Requires Fairness
• Why is this true?
• Fairness is being free from bias or injustice; evenhandedness
• But all human beings hold unconscious beliefs about different groups
• Examples
Bias Exists in Technology Too
• Software is written by humans and we’re inherently biased
• Discrimination exists in algorithms
• Most AI systems assume gender is binary
• Examples
Why We All Should Care
• To improve diversity and equality we have to detect and correct bias
• The more we learn about bias in AI, the more we learn about bias in humans
• Explainable AI is one of the top trends in the field of Machine Learning today
• US laws proposed to require large companies to audit ML systems
Creating Fair & Equitable Workplaces
• Call for ethics and explainabilty in business happening now
• Companies are taking responsibility for providing underrepresented employees
with the same treatment and opportunities as the majority
• That can’t be achieved without addressing implicit and explicit biases
• This can only be addressed by combining social science + data science
“With great power comes great responsibility”
- Peter Parker Principle
Shouldn’t Computers be Fair?
• AI algorithms aren’t necessarily biased
• Algorithms are trained on example data
• Models learn explicit or implicit biases in
the training data
• Without appropriate checks &
safeguards AI can be ruthless
• Leverages statistical differences to
make decisions
• No fairness through unawareness!
Attacking the Problem
Bias detection
• Does my data set contain bias?
• Is my model biased?
Bias explainability
• Where is the bias?
• Which are the problem features?
• What features is my model using when making a prediction?
Bias mitigation
• Can I reduce the impact of these biases?
• Should I be rectifying the data, the model or predictions?
Understand the Data
• Examine data with respect to sensitive/protected features
• Do proportion of positive outcomes vary across protected groups?
• Are features correlated with sensitive/protected features?
• Can sensitive/protected features be predicted from remaining features?
• Variety of different metrics to measure unfairness
Disparate impact =
!" #$% &$'()*+,+-./.0)
!" #$% &$)*+,+-./.0)
Consistency = 1 −
1
𝑛 . 𝑘
0
+$%
(
| 𝑘 . 𝑦𝑖 − 0
2$%
3
𝑦2 |
!
[Group fairness]
[Individual fairness]
Checking Model Bias
• Go beyond looking at overall metrics
• Aggregate stats can hide significant problems
• Model fidelity can vary significant across protected groups
• Even when overall stats are good, sub-populations may be
modeled poorly
• Breakout model stats with respect each protected group
• PPV and NPV grouped by the sensitive attribute.
• TPR, FPR, TNR and FNR grouped by the sensitive attribute.
• ROC per sensitive attribute value
Explainability
• Complex models are black boxes
• Explainability provides insights into features driving
predictions
• Possible at a global level or an individual level
• Global : what are the most important features overall
• Individual : which features are most important for an
individual prediction
• Individual explanations can be expensive
• Sample around observation and observe impact
• Train localized interpretable model approximation
https://github.com/marcotcr/lime
Local Explainability
Titanic dataset : Sex & wealth of passengers had a big impact on chance of survival
Tackling Bias
Four basic approaches to tackling bias
1. Collect ‘better’ data
2. Adjust data
3. Adjust models
4. Adjust outcome
N.B. No silver bullet
• Debiasing is not always viable
• Debiasing introduces its own bias
Data Set Manipulation
Variety of different approaches to handling data set bias
• Feature manipulation
• Modify feature values to improve CDF alignment across protected groups
• Sample weighting
• Modify sample weights to emphasize unprivileged group positive
outcomes
• Label manipulation
• Modify labels for examples close to classifier decision boundary to benefit
unprivileged group
• Dataset transformation
• Transform features and labels with group fairness, fidelity & individual
distortion constraints
Unpriv Priv
Sample weighting
Feature manipulation
Debiasing Outputs
• Multiple Thresholds
• Separate thresholds for each group value
• Maximize model performance subject to specified fairness constraint
• Outcome Modification
1. Change outcomes ‘close’ to the decision boundary
2. Probabilistically modify outcomes to achieve specified fairness objective
• Not always possible to achieve the desired fairness constraints
• Or achieve reasonable model outcomes while satisfying constraints
• Upstream intervention may be required
Bias-aware Algorithms
• Bias-aware algorithms explicitly attempt to minimize bias during training
• Algorithms leverage supplied fairness metric as explicit cost consideration
• Potentially excessively limiting in choice of algorithms
• Adversarial debiasing leverages adversarial learning to train debiased models
• Adversary attempts to predict protected group from model predictions
• Model weights are updated to better thwart adversary
• Process repeats until convergence
• Applicable to a wide range of model types
Bias in NLP
Additional opportunities for the introduction of bias
1. Embedding information
2. Pretrained models
Word Embeddings
• Map words to high dimension vectors
• Variety of different algorithms (Word2Vec, GloVe)
• ‘Similar’ words cluster together
• Arithmetic operations on word vectors
• woman - man ≈ queen - king
• Highlight stereotypical associations
• man : woman :: shopkeeper : housewife
• man : woman :: pharmaceuticals : cosmetics
• Exist for names, religions, races, genders
Man
Woman
King
Queen
𝑊 𝑘𝑖𝑛𝑔 ≈ 𝑊𝑞𝑢𝑒𝑒𝑛 − 𝑊𝑤𝑜𝑚𝑎𝑛 + 𝑊𝑚𝑎𝑛
BERT et al.
• BERT & GPT2 are common pretrained
language models
• Easily fine-tuned to perform a variety of
custom tasks
• Powerful techniques
• Rapidly increasing in popularity
• Models inherit biases observed in data
used for pretraining
• Techniques emerging for effective
debiasing
• Without impacting accuracy!
https://stereoset.mit.edu/
BERT Next Sentence Prediction
NLP Explainability
'he is an extremely unpleasant man' 'she is an extremely unpleasant woman'
Explaining BERT sentiment model
Resources
• Explainability
• LIME
• SHAP
• Bias Detection and mitigation
• TF Fairness
• AI Fairness 360
• Fairlearn
• Responsibility AI
• Debiased Embeddings
• ConceptNet
• Data sets
• Stereoset
• Documents
• FairML Book
Conclusions
• AI can be biased due to biased training data
• Responsible AI is a critical consideration for data science projects
• Develop comprehensive debiasing strategy
• Removing protected attributes is not sufficient
• Understand your data!
• Broad array of OSS solutions to help detect, explain and reduce bias
• Perform risk assessments
• Understand the implications of your AI and the impact of potential bias
• Create structure, process and governance
• No ‘wild-west’ – carefully review data, models and implications
• Diverse oversight
THANK YOU!
TO LEARN MORE, VISIT US AT RSQUARED.COM
OR EMAIL INFO@RSQUARED.COM
Additional Slides
How Does Bias Manifest?
• Many ways bias can be introduced
• Historical bias, representation bias, measurement bias, population bias
• Many human biases [Sadly]
• Over 180 human biases have been found
• Racial, gender, religious, sexual orientation, age…
• Remember : No fairness through unawareness
• Removing protected classes will not fix the problem
• Many attributes may be correlated with the protected one(s)
• Effects of bias can’t be completely eliminated
• But we can enable AI to do better in a biased world
Global Explainability
• Which features are most important
in explaining target variable
• Variety of different methods
• Model specific methods
• Feature permutation
• Drop column
• Overall behavior does not explain
individual predictions
Titanic dataset : Sex & wealth of passengers had a big
impact on chance of survival
Fairness Criteria (Classification)
Different definitions of fairness
1. Sensitive variables (A) are independent to the
prediction (R)
• Independence (R, A)
𝑃 𝑅 = 𝑟 𝐴 = 𝑎) ≥ 𝑃 𝑅 = 𝑟 𝐴 = 𝑏) − 𝜀
2. Sensitive variables are independent to error rates
• Separation (R, A, Y)
𝑃 𝑅 = 𝑟 𝑌 = 𝑞, 𝐴 = 𝑎) ≥ 𝑃 𝑅 = 𝑟 𝑌 = 𝑞, 𝐴 = 𝑏) − 𝜀
• Sufficiency (R, A, Y)
𝑃 𝑌 = 𝑞 𝑅 = 𝑟, 𝐴 = 𝑎) ≥ 𝑃 𝑌 = 𝑞 𝑅 = 𝑟, 𝐴 = 𝑏) − 𝜀
https://en.wikipedia.org/wiki/Fairness_(machine_learning)
Debiased Embeddings
• Word embeddings can be debiased
with respect to specified biases
• Debiased embeddings are now
available
• E.g. ConceptNet
• Wise to ensure that chosen
embedding has been corrected for
attributes of interest https://github.com/commonsense/conceptnet-numberbatch
Overrepresentation in Training
• Toxic example datasets without sufficient representation of words in neutral
contexts can help to significant false positives
• E.g. Gay or Black or Christian
• E.g. “I am a proud gay man” or “I am a woman who is deaf”
• See : “Jigsaw Unintended Bias in Toxicity Classification”
• May only be apparent when the model deployed
• Test data set will not highlight the problem
• Operationalized explainability can help flag problems
• Improve example datasets!

Más contenido relacionado

Similar a Using AI to Build Fair and Equitable Workplaces

AI Models For Fun and Profit by Walmart Director of Artificial Intelligence
AI Models For Fun and Profit by Walmart Director of Artificial IntelligenceAI Models For Fun and Profit by Walmart Director of Artificial Intelligence
AI Models For Fun and Profit by Walmart Director of Artificial IntelligenceProduct School
 
Data Profiling: The First Step to Big Data Quality
Data Profiling: The First Step to Big Data QualityData Profiling: The First Step to Big Data Quality
Data Profiling: The First Step to Big Data QualityPrecisely
 
Umm, how did you get that number? Managing Data Integrity throughout the Data...
Umm, how did you get that number? Managing Data Integrity throughout the Data...Umm, how did you get that number? Managing Data Integrity throughout the Data...
Umm, how did you get that number? Managing Data Integrity throughout the Data...John Kinmonth
 
Technology for everyone - AI ethics and Bias
Technology for everyone - AI ethics and BiasTechnology for everyone - AI ethics and Bias
Technology for everyone - AI ethics and BiasMarion Mulder
 
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 pillarsSofus Macskássy
 
Explainability and bias in AI
Explainability and bias in AIExplainability and bias in AI
Explainability and bias in AIBill Liu
 
Introduction to Data Analytics.pptx
Introduction to Data Analytics.pptxIntroduction to Data Analytics.pptx
Introduction to Data Analytics.pptxDikshantSharma63
 
Correlation does not mean causation
Correlation does not mean causationCorrelation does not mean causation
Correlation does not mean causationPeter Varhol
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Krishnaram Kenthapadi
 
Testing for cognitive bias in ai systems
Testing for cognitive bias in ai systemsTesting for cognitive bias in ai systems
Testing for cognitive bias in ai systemsPeter Varhol
 
Machine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional ManagersMachine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional ManagersAlbert Y. C. Chen
 
The zen of predictive modelling
The zen of predictive modellingThe zen of predictive modelling
The zen of predictive modellingQuinton Anderson
 
Building responsible AI models in Azure Machine Learning.pptx
Building responsible AI models in Azure Machine Learning.pptxBuilding responsible AI models in Azure Machine Learning.pptx
Building responsible AI models in Azure Machine Learning.pptxLuis775803
 
Towards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptxTowards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptxLuis775803
 
Olivier Blais. Model Validation Tips and Tricks to Ensure AI System Quality
Olivier Blais. Model Validation Tips and Tricks to Ensure AI System QualityOlivier Blais. Model Validation Tips and Tricks to Ensure AI System Quality
Olivier Blais. Model Validation Tips and Tricks to Ensure AI System QualityLviv Startup Club
 
Creativity and Curiosity - The Trial and Error of Data Science
Creativity and Curiosity - The Trial and Error of Data ScienceCreativity and Curiosity - The Trial and Error of Data Science
Creativity and Curiosity - The Trial and Error of Data ScienceDamianMingle
 
Myths and Realities of Psychometric Testing
Myths and Realities of Psychometric TestingMyths and Realities of Psychometric Testing
Myths and Realities of Psychometric TestingOPRA Psychology Group
 
Creating A Diverse CyberSecurity Program
Creating A Diverse CyberSecurity ProgramCreating A Diverse CyberSecurity Program
Creating A Diverse CyberSecurity ProgramTyrone Grandison
 

Similar a Using AI to Build Fair and Equitable Workplaces (20)

AI Models For Fun and Profit by Walmart Director of Artificial Intelligence
AI Models For Fun and Profit by Walmart Director of Artificial IntelligenceAI Models For Fun and Profit by Walmart Director of Artificial Intelligence
AI Models For Fun and Profit by Walmart Director of Artificial Intelligence
 
SQLDay2013_MarcinSzeliga_DataInDataMining
SQLDay2013_MarcinSzeliga_DataInDataMiningSQLDay2013_MarcinSzeliga_DataInDataMining
SQLDay2013_MarcinSzeliga_DataInDataMining
 
Data Profiling: The First Step to Big Data Quality
Data Profiling: The First Step to Big Data QualityData Profiling: The First Step to Big Data Quality
Data Profiling: The First Step to Big Data Quality
 
Umm, how did you get that number? Managing Data Integrity throughout the Data...
Umm, how did you get that number? Managing Data Integrity throughout the Data...Umm, how did you get that number? Managing Data Integrity throughout the Data...
Umm, how did you get that number? Managing Data Integrity throughout the Data...
 
Technology for everyone - AI ethics and Bias
Technology for everyone - AI ethics and BiasTechnology for everyone - AI ethics and Bias
Technology for everyone - AI ethics and Bias
 
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
 
Explainability and bias in AI
Explainability and bias in AIExplainability and bias in AI
Explainability and bias in AI
 
Introduction to Data Analytics.pptx
Introduction to Data Analytics.pptxIntroduction to Data Analytics.pptx
Introduction to Data Analytics.pptx
 
Correlation does not mean causation
Correlation does not mean causationCorrelation does not mean causation
Correlation does not mean causation
 
Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)Responsible AI in Industry (ICML 2021 Tutorial)
Responsible AI in Industry (ICML 2021 Tutorial)
 
Testing for cognitive bias in ai systems
Testing for cognitive bias in ai systemsTesting for cognitive bias in ai systems
Testing for cognitive bias in ai systems
 
Machine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional ManagersMachine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional Managers
 
Use Your Words
Use Your WordsUse Your Words
Use Your Words
 
The zen of predictive modelling
The zen of predictive modellingThe zen of predictive modelling
The zen of predictive modelling
 
Building responsible AI models in Azure Machine Learning.pptx
Building responsible AI models in Azure Machine Learning.pptxBuilding responsible AI models in Azure Machine Learning.pptx
Building responsible AI models in Azure Machine Learning.pptx
 
Towards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptxTowards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptx
 
Olivier Blais. Model Validation Tips and Tricks to Ensure AI System Quality
Olivier Blais. Model Validation Tips and Tricks to Ensure AI System QualityOlivier Blais. Model Validation Tips and Tricks to Ensure AI System Quality
Olivier Blais. Model Validation Tips and Tricks to Ensure AI System Quality
 
Creativity and Curiosity - The Trial and Error of Data Science
Creativity and Curiosity - The Trial and Error of Data ScienceCreativity and Curiosity - The Trial and Error of Data Science
Creativity and Curiosity - The Trial and Error of Data Science
 
Myths and Realities of Psychometric Testing
Myths and Realities of Psychometric TestingMyths and Realities of Psychometric Testing
Myths and Realities of Psychometric Testing
 
Creating A Diverse CyberSecurity Program
Creating A Diverse CyberSecurity ProgramCreating A Diverse CyberSecurity Program
Creating A Diverse CyberSecurity Program
 

Más de Data Con LA

Data Con LA 2022 Keynotes
Data Con LA 2022 KeynotesData Con LA 2022 Keynotes
Data Con LA 2022 KeynotesData Con LA
 
Data Con LA 2022 Keynotes
Data Con LA 2022 KeynotesData Con LA 2022 Keynotes
Data Con LA 2022 KeynotesData Con LA
 
Data Con LA 2022 Keynote
Data Con LA 2022 KeynoteData Con LA 2022 Keynote
Data Con LA 2022 KeynoteData Con LA
 
Data Con LA 2022 - Startup Showcase
Data Con LA 2022 - Startup ShowcaseData Con LA 2022 - Startup Showcase
Data Con LA 2022 - Startup ShowcaseData Con LA
 
Data Con LA 2022 Keynote
Data Con LA 2022 KeynoteData Con LA 2022 Keynote
Data Con LA 2022 KeynoteData Con LA
 
Data Con LA 2022 - Using Google trends data to build product recommendations
Data Con LA 2022 - Using Google trends data to build product recommendationsData Con LA 2022 - Using Google trends data to build product recommendations
Data Con LA 2022 - Using Google trends data to build product recommendationsData Con LA
 
Data Con LA 2022 - AI Ethics
Data Con LA 2022 - AI EthicsData Con LA 2022 - AI Ethics
Data Con LA 2022 - AI EthicsData Con LA
 
Data Con LA 2022 - Improving disaster response with machine learning
Data Con LA 2022 - Improving disaster response with machine learningData Con LA 2022 - Improving disaster response with machine learning
Data Con LA 2022 - Improving disaster response with machine learningData Con LA
 
Data Con LA 2022 - What's new with MongoDB 6.0 and Atlas
Data Con LA 2022 - What's new with MongoDB 6.0 and AtlasData Con LA 2022 - What's new with MongoDB 6.0 and Atlas
Data Con LA 2022 - What's new with MongoDB 6.0 and AtlasData Con LA
 
Data Con LA 2022 - Real world consumer segmentation
Data Con LA 2022 - Real world consumer segmentationData Con LA 2022 - Real world consumer segmentation
Data Con LA 2022 - Real world consumer segmentationData Con LA
 
Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...
Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...
Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...Data Con LA
 
Data Con LA 2022 - Moving Data at Scale to AWS
Data Con LA 2022 - Moving Data at Scale to AWSData Con LA 2022 - Moving Data at Scale to AWS
Data Con LA 2022 - Moving Data at Scale to AWSData Con LA
 
Data Con LA 2022 - Collaborative Data Exploration using Conversational AI
Data Con LA 2022 - Collaborative Data Exploration using Conversational AIData Con LA 2022 - Collaborative Data Exploration using Conversational AI
Data Con LA 2022 - Collaborative Data Exploration using Conversational AIData Con LA
 
Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...
Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...
Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...Data Con LA
 
Data Con LA 2022 - Intro to Data Science
Data Con LA 2022 - Intro to Data ScienceData Con LA 2022 - Intro to Data Science
Data Con LA 2022 - Intro to Data ScienceData Con LA
 
Data Con LA 2022 - How are NFTs and DeFi Changing Entertainment
Data Con LA 2022 - How are NFTs and DeFi Changing EntertainmentData Con LA 2022 - How are NFTs and DeFi Changing Entertainment
Data Con LA 2022 - How are NFTs and DeFi Changing EntertainmentData Con LA
 
Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...
Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...
Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...Data Con LA
 
Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...
Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...
Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...Data Con LA
 
Data Con LA 2022- Embedding medical journeys with machine learning to improve...
Data Con LA 2022- Embedding medical journeys with machine learning to improve...Data Con LA 2022- Embedding medical journeys with machine learning to improve...
Data Con LA 2022- Embedding medical journeys with machine learning to improve...Data Con LA
 
Data Con LA 2022 - Data Streaming with Kafka
Data Con LA 2022 - Data Streaming with KafkaData Con LA 2022 - Data Streaming with Kafka
Data Con LA 2022 - Data Streaming with KafkaData Con LA
 

Más de Data Con LA (20)

Data Con LA 2022 Keynotes
Data Con LA 2022 KeynotesData Con LA 2022 Keynotes
Data Con LA 2022 Keynotes
 
Data Con LA 2022 Keynotes
Data Con LA 2022 KeynotesData Con LA 2022 Keynotes
Data Con LA 2022 Keynotes
 
Data Con LA 2022 Keynote
Data Con LA 2022 KeynoteData Con LA 2022 Keynote
Data Con LA 2022 Keynote
 
Data Con LA 2022 - Startup Showcase
Data Con LA 2022 - Startup ShowcaseData Con LA 2022 - Startup Showcase
Data Con LA 2022 - Startup Showcase
 
Data Con LA 2022 Keynote
Data Con LA 2022 KeynoteData Con LA 2022 Keynote
Data Con LA 2022 Keynote
 
Data Con LA 2022 - Using Google trends data to build product recommendations
Data Con LA 2022 - Using Google trends data to build product recommendationsData Con LA 2022 - Using Google trends data to build product recommendations
Data Con LA 2022 - Using Google trends data to build product recommendations
 
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 2022 - Improving disaster response with machine learning
Data Con LA 2022 - Improving disaster response with machine learningData Con LA 2022 - Improving disaster response with machine learning
Data Con LA 2022 - Improving disaster response with machine learning
 
Data Con LA 2022 - What's new with MongoDB 6.0 and Atlas
Data Con LA 2022 - What's new with MongoDB 6.0 and AtlasData Con LA 2022 - What's new with MongoDB 6.0 and Atlas
Data Con LA 2022 - What's new with MongoDB 6.0 and Atlas
 
Data Con LA 2022 - Real world consumer segmentation
Data Con LA 2022 - Real world consumer segmentationData Con LA 2022 - Real world consumer segmentation
Data Con LA 2022 - Real world consumer segmentation
 
Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...
Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...
Data Con LA 2022 - Modernizing Analytics & AI for today's needs: Intuit Turbo...
 
Data Con LA 2022 - Moving Data at Scale to AWS
Data Con LA 2022 - Moving Data at Scale to AWSData Con LA 2022 - Moving Data at Scale to AWS
Data Con LA 2022 - Moving Data at Scale to AWS
 
Data Con LA 2022 - Collaborative Data Exploration using Conversational AI
Data Con LA 2022 - Collaborative Data Exploration using Conversational AIData Con LA 2022 - Collaborative Data Exploration using Conversational AI
Data Con LA 2022 - Collaborative Data Exploration using Conversational AI
 
Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...
Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...
Data Con LA 2022 - Why Database Modernization Makes Your Data Decisions More ...
 
Data Con LA 2022 - Intro to Data Science
Data Con LA 2022 - Intro to Data ScienceData Con LA 2022 - Intro to Data Science
Data Con LA 2022 - Intro to Data Science
 
Data Con LA 2022 - How are NFTs and DeFi Changing Entertainment
Data Con LA 2022 - How are NFTs and DeFi Changing EntertainmentData Con LA 2022 - How are NFTs and DeFi Changing Entertainment
Data Con LA 2022 - How are NFTs and DeFi Changing Entertainment
 
Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...
Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...
Data Con LA 2022 - Why Data Quality vigilance requires an End-to-End, Automat...
 
Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...
Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...
Data Con LA 2022-Perfect Viral Ad prediction of Superbowl 2022 using Tease, T...
 
Data Con LA 2022- Embedding medical journeys with machine learning to improve...
Data Con LA 2022- Embedding medical journeys with machine learning to improve...Data Con LA 2022- Embedding medical journeys with machine learning to improve...
Data Con LA 2022- Embedding medical journeys with machine learning to improve...
 
Data Con LA 2022 - Data Streaming with Kafka
Data Con LA 2022 - Data Streaming with KafkaData Con LA 2022 - Data Streaming with Kafka
Data Con LA 2022 - Data Streaming with Kafka
 

Último

➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...amitlee9823
 
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -Pooja Nehwal
 
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...gajnagarg
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...karishmasinghjnh
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...amitlee9823
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...Elaine Werffeli
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...gajnagarg
 
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...amitlee9823
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachBoston Institute of Analytics
 
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night StandCall Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...amitlee9823
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraGovindSinghDasila
 
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...gajnagarg
 
➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men 🔝mahisagar🔝 Esc...
➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men  🔝mahisagar🔝   Esc...➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men  🔝mahisagar🔝   Esc...
➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men 🔝mahisagar🔝 Esc...amitlee9823
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...amitlee9823
 
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...amitlee9823
 

Último (20)

➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
 
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
Thane Call Girls 7091864438 Call Girls in Thane Escort service book now -
 
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
Just Call Vip call girls roorkee Escorts ☎️9352988975 Two shot with one girl ...
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
👉 Amritsar Call Girl 👉📞 6367187148 👉📞 Just📲 Call Ruhi Call Girl Phone No Amri...
 
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
SAC 25 Final National, Regional & Local Angel Group Investing Insights 2024 0...
 
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Nandini Layout ☎ 7737669865 🥵 Book Your One night Stand
 
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
Just Call Vip call girls Mysore Escorts ☎️9352988975 Two shot with one girl (...
 
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
Call Girls Bommasandra Just Call 👗 7737669865 👗 Top Class Call Girl Service B...
 
Detecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning ApproachDetecting Credit Card Fraud: A Machine Learning Approach
Detecting Credit Card Fraud: A Machine Learning Approach
 
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night StandCall Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Shivaji Nagar ☎ 7737669865 🥵 Book Your One night Stand
 
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men  🔝Mathura🔝   Escorts...
➥🔝 7737669865 🔝▻ Mathura Call-girls in Women Seeking Men 🔝Mathura🔝 Escorts...
 
Aspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - AlmoraAspirational Block Program Block Syaldey District - Almora
Aspirational Block Program Block Syaldey District - Almora
 
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
Just Call Vip call girls kakinada Escorts ☎️9352988975 Two shot with one girl...
 
➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men 🔝mahisagar🔝 Esc...
➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men  🔝mahisagar🔝   Esc...➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men  🔝mahisagar🔝   Esc...
➥🔝 7737669865 🔝▻ mahisagar Call-girls in Women Seeking Men 🔝mahisagar🔝 Esc...
 
CHEAP Call Girls in Rabindra Nagar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Rabindra Nagar  (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Rabindra Nagar  (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Rabindra Nagar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men  🔝Dindigul🔝   Escor...
➥🔝 7737669865 🔝▻ Dindigul Call-girls in Women Seeking Men 🔝Dindigul🔝 Escor...
 
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
(NEHA) Call Girls Katra Call Now 8617697112 Katra Escorts 24x7
 

Using AI to Build Fair and Equitable Workplaces

  • 1. October 2020 : DCLA 2020 Using AI to Build Fair and Equitable Workplaces Sonya Balzer Dr. Lawrence Spracklen RSquared.AI
  • 2. Today’s Speakers Sonya Balzer Director of Marketing, RSquared Marketing Director, SupportLogic Dr. Lawrence Spracklen CTO, RSquared VP of Engineering & Data Science, SupportLogic VP of Engineering, Alpine Data VP of Engineering, Ayasdi
  • 3. Where We’re From • RSquared is a data-driven actionable insights platform used by organizations to improve workplace culture, inclusion and productivity • Using AI / NLP to securely analyze employee interactions and attitudes through work emails, chats, and other digital communications
  • 5. Equality Requires Fairness • Why is this true? • Fairness is being free from bias or injustice; evenhandedness • But all human beings hold unconscious beliefs about different groups • Examples
  • 6. Bias Exists in Technology Too • Software is written by humans and we’re inherently biased • Discrimination exists in algorithms • Most AI systems assume gender is binary • Examples
  • 7. Why We All Should Care • To improve diversity and equality we have to detect and correct bias • The more we learn about bias in AI, the more we learn about bias in humans • Explainable AI is one of the top trends in the field of Machine Learning today • US laws proposed to require large companies to audit ML systems
  • 8. Creating Fair & Equitable Workplaces • Call for ethics and explainabilty in business happening now • Companies are taking responsibility for providing underrepresented employees with the same treatment and opportunities as the majority • That can’t be achieved without addressing implicit and explicit biases • This can only be addressed by combining social science + data science
  • 9. “With great power comes great responsibility” - Peter Parker Principle
  • 10. Shouldn’t Computers be Fair? • AI algorithms aren’t necessarily biased • Algorithms are trained on example data • Models learn explicit or implicit biases in the training data • Without appropriate checks & safeguards AI can be ruthless • Leverages statistical differences to make decisions • No fairness through unawareness!
  • 11. Attacking the Problem Bias detection • Does my data set contain bias? • Is my model biased? Bias explainability • Where is the bias? • Which are the problem features? • What features is my model using when making a prediction? Bias mitigation • Can I reduce the impact of these biases? • Should I be rectifying the data, the model or predictions?
  • 12. Understand the Data • Examine data with respect to sensitive/protected features • Do proportion of positive outcomes vary across protected groups? • Are features correlated with sensitive/protected features? • Can sensitive/protected features be predicted from remaining features? • Variety of different metrics to measure unfairness Disparate impact = !" #$% &$'()*+,+-./.0) !" #$% &$)*+,+-./.0) Consistency = 1 − 1 𝑛 . 𝑘 0 +$% ( | 𝑘 . 𝑦𝑖 − 0 2$% 3 𝑦2 | ! [Group fairness] [Individual fairness]
  • 13. Checking Model Bias • Go beyond looking at overall metrics • Aggregate stats can hide significant problems • Model fidelity can vary significant across protected groups • Even when overall stats are good, sub-populations may be modeled poorly • Breakout model stats with respect each protected group • PPV and NPV grouped by the sensitive attribute. • TPR, FPR, TNR and FNR grouped by the sensitive attribute. • ROC per sensitive attribute value
  • 14. Explainability • Complex models are black boxes • Explainability provides insights into features driving predictions • Possible at a global level or an individual level • Global : what are the most important features overall • Individual : which features are most important for an individual prediction • Individual explanations can be expensive • Sample around observation and observe impact • Train localized interpretable model approximation https://github.com/marcotcr/lime
  • 15. Local Explainability Titanic dataset : Sex & wealth of passengers had a big impact on chance of survival
  • 16. Tackling Bias Four basic approaches to tackling bias 1. Collect ‘better’ data 2. Adjust data 3. Adjust models 4. Adjust outcome N.B. No silver bullet • Debiasing is not always viable • Debiasing introduces its own bias
  • 17. Data Set Manipulation Variety of different approaches to handling data set bias • Feature manipulation • Modify feature values to improve CDF alignment across protected groups • Sample weighting • Modify sample weights to emphasize unprivileged group positive outcomes • Label manipulation • Modify labels for examples close to classifier decision boundary to benefit unprivileged group • Dataset transformation • Transform features and labels with group fairness, fidelity & individual distortion constraints Unpriv Priv Sample weighting Feature manipulation
  • 18. Debiasing Outputs • Multiple Thresholds • Separate thresholds for each group value • Maximize model performance subject to specified fairness constraint • Outcome Modification 1. Change outcomes ‘close’ to the decision boundary 2. Probabilistically modify outcomes to achieve specified fairness objective • Not always possible to achieve the desired fairness constraints • Or achieve reasonable model outcomes while satisfying constraints • Upstream intervention may be required
  • 19. Bias-aware Algorithms • Bias-aware algorithms explicitly attempt to minimize bias during training • Algorithms leverage supplied fairness metric as explicit cost consideration • Potentially excessively limiting in choice of algorithms • Adversarial debiasing leverages adversarial learning to train debiased models • Adversary attempts to predict protected group from model predictions • Model weights are updated to better thwart adversary • Process repeats until convergence • Applicable to a wide range of model types
  • 20. Bias in NLP Additional opportunities for the introduction of bias 1. Embedding information 2. Pretrained models
  • 21. Word Embeddings • Map words to high dimension vectors • Variety of different algorithms (Word2Vec, GloVe) • ‘Similar’ words cluster together • Arithmetic operations on word vectors • woman - man ≈ queen - king • Highlight stereotypical associations • man : woman :: shopkeeper : housewife • man : woman :: pharmaceuticals : cosmetics • Exist for names, religions, races, genders Man Woman King Queen 𝑊 𝑘𝑖𝑛𝑔 ≈ 𝑊𝑞𝑢𝑒𝑒𝑛 − 𝑊𝑤𝑜𝑚𝑎𝑛 + 𝑊𝑚𝑎𝑛
  • 22. BERT et al. • BERT & GPT2 are common pretrained language models • Easily fine-tuned to perform a variety of custom tasks • Powerful techniques • Rapidly increasing in popularity • Models inherit biases observed in data used for pretraining • Techniques emerging for effective debiasing • Without impacting accuracy! https://stereoset.mit.edu/ BERT Next Sentence Prediction
  • 23. NLP Explainability 'he is an extremely unpleasant man' 'she is an extremely unpleasant woman' Explaining BERT sentiment model
  • 24. Resources • Explainability • LIME • SHAP • Bias Detection and mitigation • TF Fairness • AI Fairness 360 • Fairlearn • Responsibility AI • Debiased Embeddings • ConceptNet • Data sets • Stereoset • Documents • FairML Book
  • 25. Conclusions • AI can be biased due to biased training data • Responsible AI is a critical consideration for data science projects • Develop comprehensive debiasing strategy • Removing protected attributes is not sufficient • Understand your data! • Broad array of OSS solutions to help detect, explain and reduce bias • Perform risk assessments • Understand the implications of your AI and the impact of potential bias • Create structure, process and governance • No ‘wild-west’ – carefully review data, models and implications • Diverse oversight
  • 26. THANK YOU! TO LEARN MORE, VISIT US AT RSQUARED.COM OR EMAIL INFO@RSQUARED.COM
  • 28. How Does Bias Manifest? • Many ways bias can be introduced • Historical bias, representation bias, measurement bias, population bias • Many human biases [Sadly] • Over 180 human biases have been found • Racial, gender, religious, sexual orientation, age… • Remember : No fairness through unawareness • Removing protected classes will not fix the problem • Many attributes may be correlated with the protected one(s) • Effects of bias can’t be completely eliminated • But we can enable AI to do better in a biased world
  • 29. Global Explainability • Which features are most important in explaining target variable • Variety of different methods • Model specific methods • Feature permutation • Drop column • Overall behavior does not explain individual predictions Titanic dataset : Sex & wealth of passengers had a big impact on chance of survival
  • 30. Fairness Criteria (Classification) Different definitions of fairness 1. Sensitive variables (A) are independent to the prediction (R) • Independence (R, A) 𝑃 𝑅 = 𝑟 𝐴 = 𝑎) ≥ 𝑃 𝑅 = 𝑟 𝐴 = 𝑏) − 𝜀 2. Sensitive variables are independent to error rates • Separation (R, A, Y) 𝑃 𝑅 = 𝑟 𝑌 = 𝑞, 𝐴 = 𝑎) ≥ 𝑃 𝑅 = 𝑟 𝑌 = 𝑞, 𝐴 = 𝑏) − 𝜀 • Sufficiency (R, A, Y) 𝑃 𝑌 = 𝑞 𝑅 = 𝑟, 𝐴 = 𝑎) ≥ 𝑃 𝑌 = 𝑞 𝑅 = 𝑟, 𝐴 = 𝑏) − 𝜀 https://en.wikipedia.org/wiki/Fairness_(machine_learning)
  • 31. Debiased Embeddings • Word embeddings can be debiased with respect to specified biases • Debiased embeddings are now available • E.g. ConceptNet • Wise to ensure that chosen embedding has been corrected for attributes of interest https://github.com/commonsense/conceptnet-numberbatch
  • 32. Overrepresentation in Training • Toxic example datasets without sufficient representation of words in neutral contexts can help to significant false positives • E.g. Gay or Black or Christian • E.g. “I am a proud gay man” or “I am a woman who is deaf” • See : “Jigsaw Unintended Bias in Toxicity Classification” • May only be apparent when the model deployed • Test data set will not highlight the problem • Operationalized explainability can help flag problems • Improve example datasets!