In all goal-oriented selection activities, an existence of certain level of bias is unavoidable and may be desired for efficient artificial intelligence based decision support systems. However, a fair independent comparison of all eligible entities is essential to alleviate explicit bias in competitive marketplace. For example, searching online for a good or service, it is expected that the underlying algorithm will provide fair results by searching all available entities in the category mentioned. However, a biased search can make a narrow or collaborative query, ignoring competitive outcomes, resulting customers in costing more or getting lower quality products or services for the money they spend. This paper describes algorithmic bias in different contexts with examples and scenarios, best practices to detect bias, and two case studies to identify algorithmic bias.
This document summarizes a presentation on machine learning models, adversarial attacks, and defense strategies. It discusses adversarial attacks on machine learning systems, including GAN-based attacks. It then covers various defense strategies against adversarial attacks, such as filter-based adaptive defenses and outlier-based defenses. The presentation also addresses issues around bias in AI systems and the need for explainable and accountable AI.
[Video available at https://sites.google.com/view/ResponsibleAITutorial]
Artificial Intelligence is increasingly being used in decisions and processes that are critical for individuals, businesses, and society, especially in areas such as hiring, lending, criminal justice, healthcare, and education. Recent ethical challenges and undesirable outcomes associated with AI systems have highlighted the need for regulations, best practices, and practical tools to help data scientists and ML developers build AI systems that are secure, privacy-preserving, transparent, explainable, fair, and accountable – to avoid unintended and potentially harmful consequences and compliance challenges.
In this tutorial, we will present an overview of responsible AI, highlighting model explainability, fairness, and privacy in AI, key regulations/laws, and techniques/tools for providing understanding around AI/ML systems. Then, we will focus on the application of explainability, fairness assessment/unfairness mitigation, and privacy techniques in industry, wherein we present practical challenges/guidelines for using such techniques effectively and lessons learned from deploying models for several web-scale machine learning and data mining applications. We will present case studies across different companies, spanning many industries and application domains. Finally, based on our experiences in industry, we will identify open problems and research directions for the AI community.
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
The document discusses various ways that bias can arise in artificial intelligence systems and machine learning models. It provides examples of bias found in facial recognition systems against dark-skinned women, sentiment analysis showing preference for some religions over others, and risk assessment algorithms used in criminal justice showing racial disparities. The document also discusses definitions of fairness and bias in machine learning. It notes there are at least 21 definitions of fairness and bias can be introduced during data handling and model selection in addition to through training data.
The document discusses explainability and bias in machine learning/AI models. It covers several topics:
1. Why explainability of models is important, including for laypeople using models and potential legal needs for explanations of decisions.
2. Methods for explainability including using interpretable models directly and post-hoc explainability methods like LIME and SHAP which provide feature attributions.
3. Issues with bias in machine learning models and different definitions of fairness. It also discusses techniques for measuring and mitigating bias, such as reweighting data or using adversarial learning.
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
Responsible AI in Industry: Practical Challenges and Lessons LearnedKrishnaram Kenthapadi
How do we develop machine learning models and systems taking fairness, accuracy, explainability, and transparency into account? How do we protect the privacy of users when building large-scale AI based systems? Model fairness and explainability and protection of user privacy are considered prerequisites for building trust and adoption of AI systems in high stakes domains such as hiring, lending, and healthcare. We will first motivate the need for adopting a “fairness, explainability, and privacy by design” approach when developing AI/ML models and systems for different consumer and enterprise applications from the societal, regulatory, customer, end-user, and model developer perspectives. We will then focus on the application of responsible AI techniques in practice through industry case studies. We will discuss the sociotechnical dimensions and practical challenges, and conclude with the key takeaways and open challenges.
Responsible AI in Industry: Practical Challenges and Lessons LearnedKrishnaram Kenthapadi
How do we develop machine learning models and systems taking fairness, accuracy, explainability, and transparency into account? How do we protect the privacy of users when building large-scale AI based systems? Model fairness and explainability and protection of user privacy are considered prerequisites for building trust and adoption of AI systems in high stakes domains such as hiring, lending, and healthcare. We will first motivate the need for adopting a “fairness, explainability, and privacy by design” approach when developing AI/ML models and systems for different consumer and enterprise applications from the societal, regulatory, customer, end-user, and model developer perspectives. We will then focus on the application of responsible AI techniques in practice through industry case studies. We will discuss the sociotechnical dimensions and practical challenges, and conclude with the key takeaways and open challenges.
This document summarizes a presentation on machine learning models, adversarial attacks, and defense strategies. It discusses adversarial attacks on machine learning systems, including GAN-based attacks. It then covers various defense strategies against adversarial attacks, such as filter-based adaptive defenses and outlier-based defenses. The presentation also addresses issues around bias in AI systems and the need for explainable and accountable AI.
[Video available at https://sites.google.com/view/ResponsibleAITutorial]
Artificial Intelligence is increasingly being used in decisions and processes that are critical for individuals, businesses, and society, especially in areas such as hiring, lending, criminal justice, healthcare, and education. Recent ethical challenges and undesirable outcomes associated with AI systems have highlighted the need for regulations, best practices, and practical tools to help data scientists and ML developers build AI systems that are secure, privacy-preserving, transparent, explainable, fair, and accountable – to avoid unintended and potentially harmful consequences and compliance challenges.
In this tutorial, we will present an overview of responsible AI, highlighting model explainability, fairness, and privacy in AI, key regulations/laws, and techniques/tools for providing understanding around AI/ML systems. Then, we will focus on the application of explainability, fairness assessment/unfairness mitigation, and privacy techniques in industry, wherein we present practical challenges/guidelines for using such techniques effectively and lessons learned from deploying models for several web-scale machine learning and data mining applications. We will present case studies across different companies, spanning many industries and application domains. Finally, based on our experiences in industry, we will identify open problems and research directions for the AI community.
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
The document discusses various ways that bias can arise in artificial intelligence systems and machine learning models. It provides examples of bias found in facial recognition systems against dark-skinned women, sentiment analysis showing preference for some religions over others, and risk assessment algorithms used in criminal justice showing racial disparities. The document also discusses definitions of fairness and bias in machine learning. It notes there are at least 21 definitions of fairness and bias can be introduced during data handling and model selection in addition to through training data.
The document discusses explainability and bias in machine learning/AI models. It covers several topics:
1. Why explainability of models is important, including for laypeople using models and potential legal needs for explanations of decisions.
2. Methods for explainability including using interpretable models directly and post-hoc explainability methods like LIME and SHAP which provide feature attributions.
3. Issues with bias in machine learning models and different definitions of fairness. It also discusses techniques for measuring and mitigating bias, such as reweighting data or using adversarial learning.
[Video recording available at https://www.youtube.com/playlist?list=PLewjn-vrZ7d3x0M4Uu_57oaJPRXkiS221]
Artificial Intelligence is increasingly playing an integral role in determining our day-to-day experiences. Moreover, with proliferation of AI based solutions in areas such as hiring, lending, criminal justice, healthcare, and education, the resulting personal and professional implications of AI are far-reaching. The dominant role played by AI models in these domains has led to a growing concern regarding potential bias in these models, and a demand for model transparency and interpretability. In addition, model explainability is a prerequisite for building trust and adoption of AI systems in high stakes domains requiring reliability and safety such as healthcare and automated transportation, and critical industrial applications with significant economic implications such as predictive maintenance, exploration of natural resources, and climate change modeling.
As a consequence, AI researchers and practitioners have focused their attention on explainable AI to help them better trust and understand models at scale. The challenges for the research community include (i) defining model explainability, (ii) formulating explainability tasks for understanding model behavior and developing solutions for these tasks, and finally (iii) designing measures for evaluating the performance of models in explainability tasks.
In this tutorial, we present an overview of model interpretability and explainability in AI, key regulations / laws, and techniques / tools for providing explainability as part of AI/ML systems. Then, we focus on the application of explainability techniques in industry, wherein we present practical challenges / guidelines for effectively using explainability techniques and lessons learned from deploying explainable models for several web-scale machine learning and data mining applications. We present case studies across different companies, spanning application domains such as search & recommendation systems, hiring, sales, and lending. Finally, based on our experiences in industry, we identify open problems and research directions for the data mining / machine learning community.
Responsible AI in Industry: Practical Challenges and Lessons LearnedKrishnaram Kenthapadi
How do we develop machine learning models and systems taking fairness, accuracy, explainability, and transparency into account? How do we protect the privacy of users when building large-scale AI based systems? Model fairness and explainability and protection of user privacy are considered prerequisites for building trust and adoption of AI systems in high stakes domains such as hiring, lending, and healthcare. We will first motivate the need for adopting a “fairness, explainability, and privacy by design” approach when developing AI/ML models and systems for different consumer and enterprise applications from the societal, regulatory, customer, end-user, and model developer perspectives. We will then focus on the application of responsible AI techniques in practice through industry case studies. We will discuss the sociotechnical dimensions and practical challenges, and conclude with the key takeaways and open challenges.
Responsible AI in Industry: Practical Challenges and Lessons LearnedKrishnaram Kenthapadi
How do we develop machine learning models and systems taking fairness, accuracy, explainability, and transparency into account? How do we protect the privacy of users when building large-scale AI based systems? Model fairness and explainability and protection of user privacy are considered prerequisites for building trust and adoption of AI systems in high stakes domains such as hiring, lending, and healthcare. We will first motivate the need for adopting a “fairness, explainability, and privacy by design” approach when developing AI/ML models and systems for different consumer and enterprise applications from the societal, regulatory, customer, end-user, and model developer perspectives. We will then focus on the application of responsible AI techniques in practice through industry case studies. We will discuss the sociotechnical dimensions and practical challenges, and conclude with the key takeaways and open challenges.
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Krishnaram Kenthapadi
This document provides an overview of explainable AI techniques. It discusses how explainable AI aims to make AI models more transparent and understandable by providing explanations for their predictions. Various explanation methods are covered, including model-specific techniques like interpreting gradients in neural networks, as well as model-agnostic approaches like Shapley values from game theory. The document explains how explanations are important for building user trust in AI systems and can help with debugging, analyzing robustness, and extracting rules from complex models.
Amazon SageMaker Clarify (https://aws.amazon.com/sagemaker/clarify/) provides machine learning developers with greater visibility into their training data and models so they can identify and limit bias and explain predictions. SageMaker Clarify detects potential bias during data preparation, after model training, and in your deployed model by examining attributes you specify. For instance, you can check for bias related to age in your initial dataset or in your trained model and receive a detailed report that quantifies different types of possible bias. SageMaker Clarify also includes feature importance graphs that help you explain model predictions and produces reports which can be used to support internal presentations or to identify issues with your model that you can take steps to correct.
For more information on Amazon SageMaker Clarify, please refer these links: (1) https://aws.amazon.com/sagemaker/clarify (2) https://aws.amazon.com/blogs/aws/new-amazon-sagemaker-clarify-detects-bias-and-increases-the-transparency-of-machine-learning-models (3) https://github.com/aws/amazon-sagemaker-clarify (4) Discussion and demo: https://youtu.be/cQo2ew0DQw0
Acknowledgments: Amazon SageMaker Clarify core team, Amazon AWS AI team, and partners across Amazon
Trusted, Transparent and Fair AI using Open SourceAnimesh Singh
The document discusses IBM's efforts to bring trust and transparency to AI through open source. It outlines IBM's work on several open source projects focused on different aspects of trusted AI, including robustness (Adversarial Robustness Toolbox), fairness (AI Fairness 360), and explainability (AI Explainability 360). It provides examples of how bias can arise in AI systems and the importance of detecting and mitigating bias. The overall goal is to leverage open source to help ensure AI systems are fair, robust, and understandable through contributions to tools that can evaluate and improve trusted AI.
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Krishnaram Kenthapadi
Researchers and practitioners from different disciplines have highlighted the ethical and legal challenges posed by the use of machine learned models and data-driven systems, and the potential for such systems to discriminate against certain population groups, due to biases in algorithmic decision-making systems. This tutorial presents an overview of algorithmic bias / discrimination issues observed over the last few years and the lessons learned, key regulations and laws, and evolution of techniques for achieving fairness in machine learning systems. We motivate the need for adopting a "fairness by design" approach (as opposed to viewing algorithmic bias / fairness considerations as an afterthought), when developing machine learning based models and systems for different consumer and enterprise applications. Then, we focus on the application of fairness-aware machine learning techniques in practice by presenting non-proprietary case studies from different technology companies. Finally, based on our experiences working on fairness in machine learning at companies such as Facebook, Google, LinkedIn, and Microsoft, we present open problems and research directions for the data mining / machine learning community.
This document discusses fairness in artificial intelligence and machine learning. It begins by noting that AI can encode and amplify human biases, leading to unfair outcomes at scale. It then discusses different ways to measure fairness, such as demographic parity and equality of opportunity. The document presents an example of predicting income using census data and shows how the initial model is unfair, with low probabilities for certain groups. It explores potential sources of bias in systems and methods for enforcing fairness, such as adversarial training to iteratively train a classifier and adversarial model. The document emphasizes that fairness is complex with many approaches and no single solution, requiring active work to avoid unfair outcomes.
How do we protect privacy of users when building large-scale AI based systems? How do we develop machine learned models and systems taking fairness, accountability, and transparency into account? With the ongoing explosive growth of AI/ML models and systems, these are some of the ethical, legal, and technical challenges encountered by researchers and practitioners alike. In this talk, we will first motivate the need for adopting a "fairness and privacy by design" approach when developing AI/ML models and systems for different consumer and enterprise applications. We will then focus on the application of fairness-aware machine learning and privacy-preserving data mining techniques in practice, by presenting case studies spanning different LinkedIn applications (such as fairness-aware talent search ranking, privacy-preserving analytics, and LinkedIn Salary privacy & security design), and conclude with the key takeaways and open challenges.
NYAI #24: Developing Trust in Artificial Intelligence and Machine Learning fo...Maryam Farooq
NYAI #24: Developing Trust in Artificial Intelligence and Machine Learning for High-Stakes Applications with Dr. Kush Varshney (Principal Research Manager, IBM Research AI).
Check out the the IBM AI Fairness 360 open source toolkit: https://www.ibm.com/blogs/research/2018/09/ai-fairness-360/
nyai.co
How do we protect privacy of users when building large-scale AI based systems? How do we develop machine learned models and systems taking fairness, accountability, and transparency into account? With the ongoing explosive growth of AI/ML models and systems, these are some of the ethical, legal, and technical challenges encountered by researchers and practitioners alike. In this talk, we will first motivate the need for adopting a "fairness and privacy by design" approach when developing AI/ML models and systems for different consumer and enterprise applications. We will then focus on the application of fairness-aware machine learning and privacy-preserving data mining techniques in practice, by presenting case studies spanning different LinkedIn applications (such as fairness-aware talent search ranking, privacy-preserving analytics, and LinkedIn Salary privacy & security design), and conclude with the key takeaways and open challenges.
Privacy in AI/ML Systems: Practical Challenges and Lessons LearnedKrishnaram Kenthapadi
How do we protect the privacy of users when building large-scale AI based systems? How do we develop machine learning models and systems taking fairness, accuracy, explainability, and transparency into account? Model fairness and explainability and protection of user privacy are considered prerequisites for building trust and adoption of AI systems in high stakes domains. We will first motivate the need for adopting a “fairness, explainability, and privacy by design” approach when developing AI/ML models and systems for different consumer and enterprise applications from the societal, regulatory, customer, end-user, and model developer perspectives. We will then focus on the application of privacy-preserving AI techniques in practice through industry case studies. We will discuss the sociotechnical dimensions and practical challenges, and conclude with the key takeaways and open challenges.
An introductory take on the ethical issues surrounding the use of algorithms and machine learning in finance, education, law enforcement and defense. This work was stimulated by, but is not a product or authorized content from the IEEE P7003 WG.
Disclaimer: This work is mine alone and does not reflect view of IEEE, IEEE 7003 WG, my employer.
Algorithmic Impact Assessment: Fairness, Robustness and Explainability in Aut...Adriano Soares Koshiyama
The workshop session focuses on the following topics:
Introduction to AI & Machine Learning (Algorithms)
Key Components of Algorithmic Impact Assessment
Algorithmic Explainability
Algorithmic Fairness
Algorithmic Robustness
ML practitioners and advocates are increasingly finding themselves becoming gatekeepers of the modern world. The models you create have power to get people arrested or vindicated, get loans approved or rejected, determine what interest rate should be charged for such loans, who should be shown to you in your long list of pursuits on your Tinder, what news do you read, who gets called for a job phone screen or even a college admission... the list goes on. My goal in this talk is to summarize the kinds of disparate outcomes that are caused by cargo cult machine learning, and recent academic efforts to address some of them.
Dr Murari Mandal from NUS presented as part of 3 days OpenPOWER Industry summit about Robustness in Deep learning where he talked about AI Breakthroughs , Performance improments in AI models , Adversarial attacks , Attacks on semantic segmentation , Attacs on object detector , Defending Against adversarial attacks and many other areas.
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...Patrick Van Renterghem
In this presentation, Nazanin Gifani discussed some of the ethical and legal issues of automated decision making, including algorithmic fairness, transparency and explainability. The big question here is: can AI help us to make fairer decisions ?
Algorithms are taking control of our information rich world. As the twin sibling to Big Data, increasingly they decide how society views us via constructed profiles (as criminals? as terrorists? as rich or poor consumers?); what we see as important, newsworthy, cool or profitable (eg Twitter trending topics, automated stock selling, Amazon recommendations, BBC website top news topics etc); and indeed what we see at all as algorithms are increasingly used to filter our illegal or undesirable content as tools of public policy. Algorithms are peceived by virtue of their automation as neutral, objective and fair, unlike human decision makers - yet evidence increasingly shows the opposite - eg a series of legal complaints assert that Google games its own search results to promote its own economic interests and demote those of competitors or annoyances; while in the defamation field, French, German and Italian courts have decided that algorithmically generated autosuggests in search can be libellous (eg "Bettina Wolf prostitute"). . This paper asks if any legal remedies do or should exist to *audit* proprietary algorithms , given their importance, and asks if one way forward might be via existing and future subject access rights to personal data in EU data protection law. The transformation of these rights as proposed in the draft Data Protection Regulation is not however hopeful.
This document summarizes the background and process of developing Ethics Guidelines for Trustworthy AI by the EU's High-Level Expert Group on AI. It discusses establishing an ethical framework for AI in Europe based on principles of lawful, ethical and robust AI. The Guidelines include 7 requirements and an assessment list to operationalize the requirements, which will be piloted with stakeholders. The Expert Group will also make policy and investment recommendations to ensure Europe's competitiveness in developing trustworthy AI.
Machine Learning: Considerations for Fairly and Transparently Expanding Acces...QuantUniversity
1) The document summarizes a presentation on considerations for using machine learning to expand access to credit in a fair and transparent manner.
2) It discusses how machine learning can be used across various functions at Discover Financial Services like underwriting, customer servicing, and collections.
3) The presentation addresses challenges of interpreting complex machine learning models, ensuring fairness, and mitigating bias in models.
Robotics & Artificial (RAI) Intelligence webinar: Law & Regulation for RAI In...KTN
The Robotics & AI Innovation Network hosted a webinar addressing some of the legal and regulatory issues faced by the RAI community in the UK. Three legal experts provided their expertise to address these issues.
- Doug Bryden | Partner; Head of the Operational Risk & Environment Group, Travers Smith LLP
- Mark Richardson | Partner; IT, Telecoms and Electronics, Keltie
- Sébastien A. Krier | Founder & AI Ethics/Policy Expert, Dataphysix Ltd
In all goal-oriented selection activities, an existence
of certain level of bias is unavoidable and may be desired for
efficient artificial intelligence based decision support systems.
However, a fair independent comparison of all eligible entities is
essential to alleviate explicit bias in competitive marketplace. For
example, searching online for a good or service, it is expected that
the underlying algorithm will provide fair results by searching all
available entities in the category mentioned. However, a biased
search can make a narrow or collaborative query, ignoring
competitive outcomes, resulting customers in costing more or
getting lower quality products or services for the money they
spend. This paper describes algorithmic bias in different contexts
with examples and scenarios, best practices to detect bias, and
two case studies to identify algorithmic bias.
This presentation by Emilio Calvano, Full Professor, University of Rome and Associate Faculty, Toulouse School of Economics, was made during the discussion “Algorithmic competition” held at the 140th meeting of the OECD Competition Committee on 14 June 2023. More papers and presentations on the topic can be found out at oe.cd/algc.
This presentation was uploaded with the author’s consent.
Responsible AI in Industry (Tutorials at AAAI 2021, FAccT 2021, and WWW 2021)Krishnaram Kenthapadi
This document provides an overview of explainable AI techniques. It discusses how explainable AI aims to make AI models more transparent and understandable by providing explanations for their predictions. Various explanation methods are covered, including model-specific techniques like interpreting gradients in neural networks, as well as model-agnostic approaches like Shapley values from game theory. The document explains how explanations are important for building user trust in AI systems and can help with debugging, analyzing robustness, and extracting rules from complex models.
Amazon SageMaker Clarify (https://aws.amazon.com/sagemaker/clarify/) provides machine learning developers with greater visibility into their training data and models so they can identify and limit bias and explain predictions. SageMaker Clarify detects potential bias during data preparation, after model training, and in your deployed model by examining attributes you specify. For instance, you can check for bias related to age in your initial dataset or in your trained model and receive a detailed report that quantifies different types of possible bias. SageMaker Clarify also includes feature importance graphs that help you explain model predictions and produces reports which can be used to support internal presentations or to identify issues with your model that you can take steps to correct.
For more information on Amazon SageMaker Clarify, please refer these links: (1) https://aws.amazon.com/sagemaker/clarify (2) https://aws.amazon.com/blogs/aws/new-amazon-sagemaker-clarify-detects-bias-and-increases-the-transparency-of-machine-learning-models (3) https://github.com/aws/amazon-sagemaker-clarify (4) Discussion and demo: https://youtu.be/cQo2ew0DQw0
Acknowledgments: Amazon SageMaker Clarify core team, Amazon AWS AI team, and partners across Amazon
Trusted, Transparent and Fair AI using Open SourceAnimesh Singh
The document discusses IBM's efforts to bring trust and transparency to AI through open source. It outlines IBM's work on several open source projects focused on different aspects of trusted AI, including robustness (Adversarial Robustness Toolbox), fairness (AI Fairness 360), and explainability (AI Explainability 360). It provides examples of how bias can arise in AI systems and the importance of detecting and mitigating bias. The overall goal is to leverage open source to help ensure AI systems are fair, robust, and understandable through contributions to tools that can evaluate and improve trusted AI.
Fairness-aware Machine Learning: Practical Challenges and Lessons Learned (KD...Krishnaram Kenthapadi
Researchers and practitioners from different disciplines have highlighted the ethical and legal challenges posed by the use of machine learned models and data-driven systems, and the potential for such systems to discriminate against certain population groups, due to biases in algorithmic decision-making systems. This tutorial presents an overview of algorithmic bias / discrimination issues observed over the last few years and the lessons learned, key regulations and laws, and evolution of techniques for achieving fairness in machine learning systems. We motivate the need for adopting a "fairness by design" approach (as opposed to viewing algorithmic bias / fairness considerations as an afterthought), when developing machine learning based models and systems for different consumer and enterprise applications. Then, we focus on the application of fairness-aware machine learning techniques in practice by presenting non-proprietary case studies from different technology companies. Finally, based on our experiences working on fairness in machine learning at companies such as Facebook, Google, LinkedIn, and Microsoft, we present open problems and research directions for the data mining / machine learning community.
This document discusses fairness in artificial intelligence and machine learning. It begins by noting that AI can encode and amplify human biases, leading to unfair outcomes at scale. It then discusses different ways to measure fairness, such as demographic parity and equality of opportunity. The document presents an example of predicting income using census data and shows how the initial model is unfair, with low probabilities for certain groups. It explores potential sources of bias in systems and methods for enforcing fairness, such as adversarial training to iteratively train a classifier and adversarial model. The document emphasizes that fairness is complex with many approaches and no single solution, requiring active work to avoid unfair outcomes.
How do we protect privacy of users when building large-scale AI based systems? How do we develop machine learned models and systems taking fairness, accountability, and transparency into account? With the ongoing explosive growth of AI/ML models and systems, these are some of the ethical, legal, and technical challenges encountered by researchers and practitioners alike. In this talk, we will first motivate the need for adopting a "fairness and privacy by design" approach when developing AI/ML models and systems for different consumer and enterprise applications. We will then focus on the application of fairness-aware machine learning and privacy-preserving data mining techniques in practice, by presenting case studies spanning different LinkedIn applications (such as fairness-aware talent search ranking, privacy-preserving analytics, and LinkedIn Salary privacy & security design), and conclude with the key takeaways and open challenges.
NYAI #24: Developing Trust in Artificial Intelligence and Machine Learning fo...Maryam Farooq
NYAI #24: Developing Trust in Artificial Intelligence and Machine Learning for High-Stakes Applications with Dr. Kush Varshney (Principal Research Manager, IBM Research AI).
Check out the the IBM AI Fairness 360 open source toolkit: https://www.ibm.com/blogs/research/2018/09/ai-fairness-360/
nyai.co
How do we protect privacy of users when building large-scale AI based systems? How do we develop machine learned models and systems taking fairness, accountability, and transparency into account? With the ongoing explosive growth of AI/ML models and systems, these are some of the ethical, legal, and technical challenges encountered by researchers and practitioners alike. In this talk, we will first motivate the need for adopting a "fairness and privacy by design" approach when developing AI/ML models and systems for different consumer and enterprise applications. We will then focus on the application of fairness-aware machine learning and privacy-preserving data mining techniques in practice, by presenting case studies spanning different LinkedIn applications (such as fairness-aware talent search ranking, privacy-preserving analytics, and LinkedIn Salary privacy & security design), and conclude with the key takeaways and open challenges.
Privacy in AI/ML Systems: Practical Challenges and Lessons LearnedKrishnaram Kenthapadi
How do we protect the privacy of users when building large-scale AI based systems? How do we develop machine learning models and systems taking fairness, accuracy, explainability, and transparency into account? Model fairness and explainability and protection of user privacy are considered prerequisites for building trust and adoption of AI systems in high stakes domains. We will first motivate the need for adopting a “fairness, explainability, and privacy by design” approach when developing AI/ML models and systems for different consumer and enterprise applications from the societal, regulatory, customer, end-user, and model developer perspectives. We will then focus on the application of privacy-preserving AI techniques in practice through industry case studies. We will discuss the sociotechnical dimensions and practical challenges, and conclude with the key takeaways and open challenges.
An introductory take on the ethical issues surrounding the use of algorithms and machine learning in finance, education, law enforcement and defense. This work was stimulated by, but is not a product or authorized content from the IEEE P7003 WG.
Disclaimer: This work is mine alone and does not reflect view of IEEE, IEEE 7003 WG, my employer.
Algorithmic Impact Assessment: Fairness, Robustness and Explainability in Aut...Adriano Soares Koshiyama
The workshop session focuses on the following topics:
Introduction to AI & Machine Learning (Algorithms)
Key Components of Algorithmic Impact Assessment
Algorithmic Explainability
Algorithmic Fairness
Algorithmic Robustness
ML practitioners and advocates are increasingly finding themselves becoming gatekeepers of the modern world. The models you create have power to get people arrested or vindicated, get loans approved or rejected, determine what interest rate should be charged for such loans, who should be shown to you in your long list of pursuits on your Tinder, what news do you read, who gets called for a job phone screen or even a college admission... the list goes on. My goal in this talk is to summarize the kinds of disparate outcomes that are caused by cargo cult machine learning, and recent academic efforts to address some of them.
Dr Murari Mandal from NUS presented as part of 3 days OpenPOWER Industry summit about Robustness in Deep learning where he talked about AI Breakthroughs , Performance improments in AI models , Adversarial attacks , Attacks on semantic segmentation , Attacs on object detector , Defending Against adversarial attacks and many other areas.
Fairness and Transparency: Algorithmic Explainability, some Legal and Ethical...Patrick Van Renterghem
In this presentation, Nazanin Gifani discussed some of the ethical and legal issues of automated decision making, including algorithmic fairness, transparency and explainability. The big question here is: can AI help us to make fairer decisions ?
Algorithms are taking control of our information rich world. As the twin sibling to Big Data, increasingly they decide how society views us via constructed profiles (as criminals? as terrorists? as rich or poor consumers?); what we see as important, newsworthy, cool or profitable (eg Twitter trending topics, automated stock selling, Amazon recommendations, BBC website top news topics etc); and indeed what we see at all as algorithms are increasingly used to filter our illegal or undesirable content as tools of public policy. Algorithms are peceived by virtue of their automation as neutral, objective and fair, unlike human decision makers - yet evidence increasingly shows the opposite - eg a series of legal complaints assert that Google games its own search results to promote its own economic interests and demote those of competitors or annoyances; while in the defamation field, French, German and Italian courts have decided that algorithmically generated autosuggests in search can be libellous (eg "Bettina Wolf prostitute"). . This paper asks if any legal remedies do or should exist to *audit* proprietary algorithms , given their importance, and asks if one way forward might be via existing and future subject access rights to personal data in EU data protection law. The transformation of these rights as proposed in the draft Data Protection Regulation is not however hopeful.
This document summarizes the background and process of developing Ethics Guidelines for Trustworthy AI by the EU's High-Level Expert Group on AI. It discusses establishing an ethical framework for AI in Europe based on principles of lawful, ethical and robust AI. The Guidelines include 7 requirements and an assessment list to operationalize the requirements, which will be piloted with stakeholders. The Expert Group will also make policy and investment recommendations to ensure Europe's competitiveness in developing trustworthy AI.
Machine Learning: Considerations for Fairly and Transparently Expanding Acces...QuantUniversity
1) The document summarizes a presentation on considerations for using machine learning to expand access to credit in a fair and transparent manner.
2) It discusses how machine learning can be used across various functions at Discover Financial Services like underwriting, customer servicing, and collections.
3) The presentation addresses challenges of interpreting complex machine learning models, ensuring fairness, and mitigating bias in models.
Robotics & Artificial (RAI) Intelligence webinar: Law & Regulation for RAI In...KTN
The Robotics & AI Innovation Network hosted a webinar addressing some of the legal and regulatory issues faced by the RAI community in the UK. Three legal experts provided their expertise to address these issues.
- Doug Bryden | Partner; Head of the Operational Risk & Environment Group, Travers Smith LLP
- Mark Richardson | Partner; IT, Telecoms and Electronics, Keltie
- Sébastien A. Krier | Founder & AI Ethics/Policy Expert, Dataphysix Ltd
In all goal-oriented selection activities, an existence
of certain level of bias is unavoidable and may be desired for
efficient artificial intelligence based decision support systems.
However, a fair independent comparison of all eligible entities is
essential to alleviate explicit bias in competitive marketplace. For
example, searching online for a good or service, it is expected that
the underlying algorithm will provide fair results by searching all
available entities in the category mentioned. However, a biased
search can make a narrow or collaborative query, ignoring
competitive outcomes, resulting customers in costing more or
getting lower quality products or services for the money they
spend. This paper describes algorithmic bias in different contexts
with examples and scenarios, best practices to detect bias, and
two case studies to identify algorithmic bias.
This presentation by Emilio Calvano, Full Professor, University of Rome and Associate Faculty, Toulouse School of Economics, was made during the discussion “Algorithmic competition” held at the 140th meeting of the OECD Competition Committee on 14 June 2023. More papers and presentations on the topic can be found out at oe.cd/algc.
This presentation was uploaded with the author’s consent.
Presentation delivered at the EUI in Florence during the FSR C&M, CMPF and FCP Annual Scientific Seminar on 'Competition, Regulation and Pluralism in the Online World' (22-23 March 2018).
Machine learning is a method of data analysis that uses algorithms to iteratively learn from data without being explicitly programmed. It allows computers to find hidden insights in data and become better at tasks via experience. Machine learning has many practical applications and is important due to growing data availability, cheaper and more powerful computation, and affordable storage. It is used in fields like finance, healthcare, marketing and transportation. The main approaches are supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Each has real-world examples like loan prediction, market basket analysis, webpage classification, and marketing campaign optimization.
SALESmanago Marketing Automation has developed its own AI engine – SALESmanago Copernicus Machine Learning&AI. Just now companies such as New Balance, Yves Rocher and Sizeer are using it to provide their customers with tailored and intelligently personalized content.
https://www.learntek.org/machine-learning-using-spark/
https://www.learntek.org
Learntek is global online training provider on Big Data Analytics, Hadoop, Machine Learning, Deep Learning, IOT, AI, Cloud Technology, DEVOPS, Digital Marketing and other IT and Management courses.
AI is the study and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, and decision-making. Key applications of AI include advanced web search, recommendation systems, speech recognition in digital assistants, self-driving cars, and game playing. The goal of AI is to create systems that can think and act rationally. While progress has been made, fully simulating human intelligence remains a challenge.
On the Diversity of the Accountability Problem. Machine Learning and Knowing ...Bernhard Rieder
This document discusses the accountability problem with machine learning algorithms. It notes that there are two types of algorithms - those explicitly coded and those that learn statistical patterns in data. These latter types can be difficult to assess and shift the focus from normative values to empirical patterns in data. It also discusses how algorithms can learn sensitive personal attributes from innocuous Facebook likes and how risk algorithms associate many data points with loan default risk. The document argues that accountability is not enough and that regulation will need to be domain-specific while exploring approaches like consumer protections and data restrictions. It concludes that algorithms reflect societal structures and turning this into profit always raises normative issues requiring attention to commercial influences and consideration of more egalitarian alternatives.
A study on the chain restaurants dynamic negotiation games of the optimizatio...ijcsit
In the era of meager profit, production costs often become an important factor affecting SMEs’ operating
conditions, and how to effectively reduce production costs has become an issue of in-depth consideration
for the business owners. Especially, the food and beverage (F&B) industry cannot accurately predict the
demand. It many cause demand forecast fall and excess or insufficient inventory pressure. Companies of
the F&B industry may be even unable to meet immediate customer needs. They are faced great challenges
in quick response and inventory pressure. This study carried out the product inventory model analysis of
the most recent year’s sales data of the fresh food materials for chain restaurants in a supply chain region
with raw material suppliers and demanders. Moreover, this study adopted the multi-agent dynamic strategy
game to establish the joint procurement decision model negotiation algorithm for analysis and verification
by simulation cases to achieve the design of dynamic negotiation optimization mechanism for the joint
procurement of food materials. Coupled with supply chain management 3C theory for food material
inventory management, we developed the optimization method for determining the order quantities of the
chain restaurants. For product demand forecast, we applied the commonality model, production and
delivery capacity model, and the model of consumption and replenishment based on market demand
changes in categorization and development. Moreover, with the existence of dependencies between product
demands as the demand forecast basis, we determined the appropriate inventory model accordingly.
1) Deep learning has advanced rapidly in recent years due to large datasets, distributed computing, and GPUs. This has led to practical applications in areas like targeted marketing, predictive analytics, improved decision making, increased productivity, and retail automation.
2) Companies are using deep learning to better target customers through personalized recommendations, local pricing strategies, and predictive advertising. AI is also improving decision making in areas like emergency response, criminal investigations, and sports coaching.
3) Deep learning is driving productivity gains through automation of tasks like construction monitoring, machinery maintenance, and parts of the recruitment process. Areas like retail are being transformed by applications such as computer vision, dynamic pricing, and augmented reality recommendations.
1) Deep learning has advanced rapidly in recent years due to large datasets, distributed computing, and GPUs. This has led to practical applications in areas like targeted marketing, predictive analytics, improved decision making, increased productivity, and retail automation.
2) Companies are using deep learning to better target customers through personalized recommendations, local pricing strategies, and predictive advertising. AI is also improving decision making in areas like emergency response, criminal investigations, and sports coaching.
3) Deep learning is driving productivity gains through automation of tasks like construction monitoring, machinery maintenance, and parts of the recruitment process. Areas like retail are being transformed by applications such as computer vision, dynamic pricing, and augmented reality recommendations.
The Ethical Considerations of AI in Retail_ Bias, Transparency, and User Priv...tamizhias2003
Mindnotix is an exclusive web and mobile app development company with 12+ years of experience and 400+ happy clients in India, US, UK and Middle East. We Provide Complete solution on disruptive technologies like AR, VR , IOT and AI app developments.
Measures and mismeasures of algorithmic fairnessManojit Nandi
This document discusses various measures and challenges of achieving algorithmic fairness. It begins by defining algorithmic fairness and noting it is inherently a social concept. It then covers three main types of algorithmic biases: bias in allocation, representation, and weaponization. It outlines three families of fairness measures: anti-classification, classification parity, and calibration. It notes each approach has dangers and no single definition of fairness exists. The document concludes by discussing proposed standards for documenting datasets and models to improve algorithmic transparency and accountability.
This paper is an analysis on the impact machine learning, Artificial Intelligence, and robotics has on
the supply chain management. The analysis covers the basis of AI in the SCM mechanisms while defining it
from the ground up. Later on, to shed a true light on supply first the paper zooms in on the effects of machines
in marketing.
ifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and morehen_drik
The document summarizes several papers presented at CHI 2018 on the topics of:
1) Understanding user experience of co-creation with AI through a drawing collaboration study.
2) Perceptions of justice and fairness in algorithmic decision-making through experimental studies.
3) A qualitative study of perceptions of algorithmic fairness among marginalized groups.
4) The effects of communicating advertising algorithm processes on user perceptions and trust.
ARTIFICIAL INTELLIGENCE AND ETHICS 29.pptxAmalaPaulson
This document discusses human-centered design approaches to AI, potential harms of machine learning systems, and ways to address bias and promote fairness. It outlines six types of bias that can occur, including historical, representation, measurement, aggregation, evaluation and deployment bias. It also describes four common fairness criteria: demographic parity, equal opportunity, equal accuracy, and group unawareness. The document explains that model cards can be used to promote transparency by documenting key details about machine learning models, including intended uses, technical information, and evaluations of model performance and limitations.
Overview of public concerns and regulatory interest in issues algorithm transparency, accountability and fairness, with background information about the technical/design origin of these issues.
Reinforcement learning is the next revolution in artificial intelligence (AI). As a feedback-driven and agent-based learning technology stack that is suitable for dynamic environments, reinforcement learning methodologies leverage self-learning capabilities and multi-agent potential to address issues that are unaddressed by other AI techniques. In contrast, other machine learning, AI techniques like supervised learning and unsupervised learning are limited to handling one task at a given time.
With the advent of Artificial General Intelligence (AGI), reinforcement learning becomes important in addressing other challenges like multi-tasking of intelligent applications across different ecosystems. The technology appears set to drive the adoption of AGI technologies, with companies futureproofing their AGI roadmaps by leveraging reinforcement learning techniques.
This report provides an analysis of the startups focused on reinforcement learning techniques across industries. To purchase the complete report visit https://www.researchonglobalmarkets.com/reinforcement-learning-startup-ecosystem-analysis.html.
Netscribes offers customizations to this report depending on your specific needs. To request a customized report, contact info@netscribes.com.
To purchase the full report, write to us at info@netscribes.com
Economic design in cryptoeconomics_game theory_mechanism design_market design...Jongseung Kim
Game theory, mechanism design, and market design provide tools to analyze strategic interactions between rational decision-makers. Mechanism design aims to incentivize truthful behavior through game design, using concepts like Nash equilibrium and incentive compatibility. Market design applies these tools to design markets that efficiently match agents, such as through auctions and stable matching algorithms. Cryptoeconomics applies these economic principles to distributed systems like blockchains, using cryptography to guarantee economic mechanisms and incentives.
Similar to An empirical study on algorithmic bias (aiml compsac2020) (20)
Generative adversarial networks (GANs) are a class of machine learning frameworks where two neural networks contest with each other in a game. One network generates new data instances, while the other evaluates them for authenticity. The generator creates synthetic instances to fool the discriminator, while the discriminator learns to identify the generator's fakes from true instances.
Interpretable Learning Model for Lower Dimensional Feature Space: A Case stud...Kishor Datta Gupta
Detecting brown spot in rice leaf is an urgent complication in the agricultural field as Brown Spot disease lessen the rice yield remarkably. Several segmentation techniques have been applied to identify and extract the infected portion of the rice-leaf and machine learning algorithms such as decision trees, support vector machines are applied to detect this infection. In particular, a combination of Convolution Neural Networks with these algorithms has also tried to resolve this problem. Although this attempt has achieved success in providing accuracy (96.8%), these kinds of approaches raise issues regarding the size and interpretability of feature space and interpretability of the decision model. Indeed, Deep learning networks automatically create a feature space that usually contains a massive number of features (numerous of them are not necessarily appropriate). This vast number of features extends the non-interpretability of the machine learning model. Furthermore, training the model with these many features is computationally expensive. To resolve these issues, we propose a method to extract a few interpretable features from rice-leaf images and construct a low-dimensional feature space; however, interpretation shows that they deserve significant credit for the decent accuracy of our classification model.
A safer approach to build recommendation systems on unidentifiable dataKishor Datta Gupta
Conference: 14th International Conference on Agents and Artificial Intelligence (ICAART 2022)
In recent years, data security has been one of the biggest concerns, and individuals have grown increasingly worried about the security of their personal information. Personalization typically necessitates the collection of individual data for analysis, exposing customers to privacy concerns. Companies create an illusion of safety to make people feel safe using a mainstream word, "encryption". Though encryption protects personal data from an external breach, the companies can still exploit personal data collected from users as they own the encryption keys. We present a naive yet secure approach for recommending movies to consumers without collecting any personally identifiable information. Our proposed approach can assist a movie recommendation system understand user preferences using the user's movie watch-time and watch history only. We conducted a comprehensive and comparative study on the performance of three deep reinforcement learning architectures, namely DQN, DDQN, and D3QN, on the same task. We observed that D3QN outperformed the other two architectures and achieved a precision of 0.880, recall of 0.805, and F1 score of 0.830. The results show that we can build a competitive movie recommendation system using unidentifiable data.
The document discusses adversarial attacks (AAs) on AI/ML systems. It outlines different types of attacks like poisoning attacks, evasion attacks, and Trojan attacks. It also describes various evasion-based attack methods like one pixel attacks and gradient attacks. Additionally, it notes that AAs can be transferable between models and are less effective in physical environments. The document discusses current defense strategies like retraining models, input reconstruction, and model modifications. However, it notes limitations like reduced accuracy and vulnerability to adaptive attacks. It also does not sufficiently test defense practicality or computational costs. In conclusion, the document argues that defending against adaptive attacks and Trojan attacks is particularly challenging and requires end-to-end protections.
Robust Filtering Schemes for Machine Learning Systems to Defend Adversarial A...Kishor Datta Gupta
This presentation discusses robust filtering schemes to defend machine learning systems against adversarial attacks. It outlines three main defense schemes: input filtering, output filtering, and an end-to-end protection scheme. The input filtering scheme uses a genetic algorithm to determine an optimal sequence of filters to detect adversarial examples. The output filtering scheme formulates the detection of adversarial inputs as an outlier detection problem. The end-to-end scheme integrates components for adversarial detection, filtering, and classification into a unified framework for protection. Experimental results show the proposed approaches can effectively detect various adversarial attack types while maintaining high classification accuracy.
Zero-shot learning allows a model to recognize classes that it was not trained on by utilizing auxiliary information about both seen and unseen classes during training. The model is trained to predict this auxiliary information, like word embeddings or manually designed features, for the seen classes. During testing, the model predicts the auxiliary information for an unseen class and assigns it to the class whose auxiliary information is closest, even if that class was not part of the training data. This allows the model to generalize to new classes without requiring labeled examples of those classes.
Using Negative Detectors for Identifying Adversarial Data Manipulation in Mac...Kishor Datta Gupta
With the increased popularity of Machine Learning (ML) in real-world applications, adversarial attacks are emerging to subvert the ML-based decision support systems. It appears that the existing adversarial defenses are ineffective against adaptive attacks since these are highly depend on knowledge of prior attacks and the ML model architecture. To alleviate the challenges, We propose a negative filtering strategy that does not require any adversarial knowledge and can work independent of ML models. This filtering strategy relies on salient features of clean (training) data and employs a complementary approach to cover possible attack surface in an application. Our empirical experiments with different data sets demonstrate that the negative filters could effectively detect wide-range of adversarial inputs and update itself to protect against adaptive attacks.
Deep Reinforcement Learning based Recommendation with Explicit User-ItemInter...Kishor Datta Gupta
—Recommendation is crucial in both academia andindustry, and various techniques are proposed such as content-based collaborative filtering, matrix factorization, logistic re-gression, factorization machines, neural networks and multi-armed bandits. However, most of the previous studies sufferfrom two limitations: (1) considering the recommendation asa static procedure and ignoring the dynamic interactive naturebetween users and the recommender systems; (2) focusing on theimmediate feedback of recommended items and neglecting thelong-term rewards. To address the two limitations, in this paperwe propose a novel recommendation framework based on deepreinforcement learning, called DRR. The DRR framework treatsrecommendation as a sequential decision making procedure andadopts an “Actor-Critic” reinforcement learning scheme to modelthe interactions between the users and recommender systems,which can consider both the dynamic adaptation and long-term rewards. Further more, a state representation module isincorporated into DRR, which can explicitly capture the interac-tions between items and users. Three instantiation structures aredeveloped. Extensive experiments on four real-world datasets areconducted under both the offline and online evaluation settings.The experimental results demonstrate the proposed DRR methodindeed outperforms the state-of-the-art competitors
Machine learning can be applied in various areas of computer security like network security, endpoint protection, application security, user behavior analysis, and process behavior analysis. Some common machine learning techniques that are useful for security include regression for prediction and detection of anomalies, classification to identify threats and attacks, and clustering for forensic analysis and to detect outliers. Example applications of machine learning in security include using regression to detect anomalies in network traffic, classification to identify malware, and clustering to separate malware from legitimate files.
Policy Based reinforcement Learning for time series Anomaly detectionKishor Datta Gupta
This document discusses a policy-based reinforcement learning approach called PTAD for time series anomaly detection. PTAD formulates anomaly detection as a Markov Decision Process and uses an asynchronous actor-critic algorithm to learn a stochastic policy. The agent takes as input current and previous time series data and actions, and outputs a decision of normal or anomalous. It is rewarded based on a confusion matrix calculation. Experimental results show PTAD achieves best performance both within and across datasets by adjusting to different behaviors. The stochastic policy allows exploring precision-recall tradeoffs. While interesting, it is not compared to neural network based techniques like autoencoders.
This document discusses intrusion detection systems (IDS). It covers the key components of an IDS, including methods of intrusion detection like audit trail processing, on-the-fly processing, profiles of normal behavior, signatures of abnormal behavior, and parameter pattern matching. The document also discusses building network-based IDS using tools like Snort and host-based IDS. It provides examples of labs to analyze network and wireless intrusion detection using machine learning techniques.
understanding the pandemic through mining covid news using natural language p...Kishor Datta Gupta
This document summarizes a research presentation on analyzing Covid-19 news reports from newspapers in developed and developing countries using natural language processing. It introduces the research aim to understand how newspapers portray the pandemic using NLP techniques on reports from the US and Bangladesh. The researchers collected over 1000 news articles to create the NNK Dataset, which they preprocessed and analyzed to extract keywords, sentiments, and case numbers. Word clouds of frequent terms and numeric extractions showed how coverage evolved over time. The dataset was made publicly available to encourage further analysis of portraying pandemics through newspapers.
The document discusses using different representation spaces for digits when classifying MNIST data. It shows that classifying digits when each digit has its own best representation space that other digits are compared to leads to much higher accuracy, ranging from 97-99%, compared to using the same representation space for all digits which only achieves 64% accuracy.
"Can NLP techniques be utilized as a reliable tool for medical science?" -Bui...Kishor Datta Gupta
Artificial intelligence persists on being a right-hand tool for many branches of biology. From preliminary advices and treatments, such as understanding if symptoms related to fever or cold, to critical detection of cancerous cell or classification of X-rays, traditional machine learning and deep learning techniques achieved remarkable feats. However, total dependency on machine-based prediction is yet a far fetched concept. In this paper, we provide a framework utilizing several Natural Language Processing (NLP) algorithms to construct a comparative analysis. We create an ensemble of top-performing algorithms to accomplish classification task on medical reports. We compare both the traditional machine learning and deep learning techniques and evaluate their probabilities of being reliable on analyzing medical diagnosis. We concluded that an ensemble approach can provide reliable outcomes with accuracy over 92% and that the current state of the art is unequipped to provide the result with the standard needed for health sectors but an ensemble of these techniques can be a pathway for future research direction.
Conference: IEEE 11th Annual Information Technology, Electronics and Mobile Communication Conference (IEEE IEMCON 2020)At: Vancouver
Applicability issues of Evasion-Based Adversarial Attacks and Mitigation Tech...Kishor Datta Gupta
Adversarial attacks are considered security risks for Artificial Intelligence-based systems. Researchers have been studying different defense techniques appropriate for adversarial attacks. Evaluation strategies of these attacks and corresponding defenses are primarily conducted on trivial benchmark analysis. We have observed that most of these analyses have practical limitations for both attacks and for defense methods. In this work, we analyzed the adversarial attacks based on how these are performed in real-world problems and what steps can be taken to mitigate their effects. We also studied practicability issues of well-established defense techniques against adversarial attacks and proposed some guidelines for better and effective solutions. We demonstrated that the adversarial attacks detection rate and destruction rate co-related inversely, which can be used in designing defense techniques. Based on our experimental results, we suggest an adversarial defense model incorporating security policies that are suitable for practical purposes.
https://www.researchgate.net/publication/344463103_Applicability_issues_of_Evasion-Based_Adversarial_Attacks_and_Mitigation_Techniques
Adversarial Input Detection Using Image Processing Techniques (IPT)Kishor Datta Gupta
Modern deep learning models for the computer vision domain are vulnerable against adversarial attacks. Image prepossessing technique based defense against malicious input is currently considered obsolete as this defense is not effective against all types of attacks. The advanced adaptive attack can easily defeat pre-processing based defenses. In this paper, we proposed a framework that will generate a set of image processing sequences (several image processing techniques in a series). We randomly select a set of Image processing technique sequences (IPTS) dynamically to answer the obscurity question in testing time. This paper outlines methodology utilizing varied datasets examined with various adversarial data manipulations. For specific attack types and dataset, it produces unique IPTS. The outcome of our empirical experiments shows that the method can efficiently employ as processing for any machine learning models. The research also showed that our process works against adaptive attacks as we are using a non-deterministic set of IPTS for each adversarial input.
This document discusses clustering clean and adversarial images from the MNIST dataset using K-means, LDA, and T-SNE clustering methods. It contains 10,000 clean images and 10,000 adversarial images generated using the FGSM attack method from 10 classes in MNIST. The document applies principal component analysis to extract features from the images before clustering them to visualize how the different methods group the clean and adversarial samples.
This document discusses basic digital image concepts including image data representations, color channels, bit depth, CMYK vs RGB color models, image blur filters using kernels, and kernel operations used in convolutional neural networks (CNN).
Hybrid pow-pos-based-system against majority attack-in-cryptocurrency system ...Kishor Datta Gupta
This document proposes a hybrid PoW-PoS consensus protocol to prevent 51% attacks in cryptocurrency systems. The key points are:
1) A 51% attack occurs when a single entity gains over 50% of the network's computational power, allowing them to manipulate the blockchain.
2) Existing solutions have limitations like special validators, inconsistent block times, or reliance on another network.
3) The proposed solution uses PoW and PoS sequentially in each node, adjusting difficulty to maintain consistent block times. It penalizes malicious nodes and distributes profits proportionally.
4) Analysis shows the hybrid protocol maintains decentralization and the blockchain properties better than alternatives like Casper, Decred or Komodo
Shamir secret sharing: Alternative of hashing for authenticationKishor Datta Gupta
Hashing is vulnerable to quantum attack. So keep password text hidden using hash in quantum computer era is not viable. Shamir's secret sharing can be used for authentication purpose as a alternative of hashing
Literature Review Basics and Understanding Reference Management.pptxDr Ramhari Poudyal
Three-day training on academic research focuses on analytical tools at United Technical College, supported by the University Grant Commission, Nepal. 24-26 May 2024
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...University of Maribor
Slides from talk presenting:
Aleš Zamuda: Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapter and Networking.
Presentation at IcETRAN 2024 session:
"Inter-Society Networking Panel GRSS/MTT-S/CIS
Panel Session: Promoting Connection and Cooperation"
IEEE Slovenia GRSS
IEEE Serbia and Montenegro MTT-S
IEEE Slovenia CIS
11TH INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONIC AND COMPUTING ENGINEERING
3-6 June 2024, Niš, Serbia
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
KuberTENes Birthday Bash Guadalajara - K8sGPT first impressionsVictor Morales
K8sGPT is a tool that analyzes and diagnoses Kubernetes clusters. This presentation was used to share the requirements and dependencies to deploy K8sGPT in a local environment.
International Conference on NLP, Artificial Intelligence, Machine Learning an...gerogepatton
International Conference on NLP, Artificial Intelligence, Machine Learning and Applications (NLAIM 2024) offers a premier global platform for exchanging insights and findings in the theory, methodology, and applications of NLP, Artificial Intelligence, Machine Learning, and their applications. The conference seeks substantial contributions across all key domains of NLP, Artificial Intelligence, Machine Learning, and their practical applications, aiming to foster both theoretical advancements and real-world implementations. With a focus on facilitating collaboration between researchers and practitioners from academia and industry, the conference serves as a nexus for sharing the latest developments in the field.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
A review on techniques and modelling methodologies used for checking electrom...nooriasukmaningtyas
The proper function of the integrated circuit (IC) in an inhibiting electromagnetic environment has always been a serious concern throughout the decades of revolution in the world of electronics, from disjunct devices to today’s integrated circuit technology, where billions of transistors are combined on a single chip. The automotive industry and smart vehicles in particular, are confronting design issues such as being prone to electromagnetic interference (EMI). Electronic control devices calculate incorrect outputs because of EMI and sensors give misleading values which can prove fatal in case of automotives. In this paper, the authors have non exhaustively tried to review research work concerned with the investigation of EMI in ICs and prediction of this EMI using various modelling methodologies and measurement setups.
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELgerogepatton
As digital technology becomes more deeply embedded in power systems, protecting the communication
networks of Smart Grids (SG) has emerged as a critical concern. Distributed Network Protocol 3 (DNP3)
represents a multi-tiered application layer protocol extensively utilized in Supervisory Control and Data
Acquisition (SCADA)-based smart grids to facilitate real-time data gathering and control functionalities.
Robust Intrusion Detection Systems (IDS) are necessary for early threat detection and mitigation because
of the interconnection of these networks, which makes them vulnerable to a variety of cyberattacks. To
solve this issue, this paper develops a hybrid Deep Learning (DL) model specifically designed for intrusion
detection in smart grids. The proposed approach is a combination of the Convolutional Neural Network
(CNN) and the Long-Short-Term Memory algorithms (LSTM). We employed a recent intrusion detection
dataset (DNP3), which focuses on unauthorized commands and Denial of Service (DoS) cyberattacks, to
train and test our model. The results of our experiments show that our CNN-LSTM method is much better
at finding smart grid intrusions than other deep learning algorithms used for classification. In addition,
our proposed approach improves accuracy, precision, recall, and F1 score, achieving a high detection
accuracy rate of 99.50%.
6th International Conference on Machine Learning & Applications (CMLA 2024)ClaraZara1
6th International Conference on Machine Learning & Applications (CMLA 2024) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Applications.
6th International Conference on Machine Learning & Applications (CMLA 2024)
An empirical study on algorithmic bias (aiml compsac2020)
1. An Empirical Study on
Algorithmic Bias
Sajib Sen, Dipankar Dasgupta, Kishor Datta Gupta
University of Memphis
2. Overview
• Different type of bias.
• Categories of Algorithmic bias.
• Scenarios and examples of algorithmic bias.
• Explainable AI.
• Case Study.
3. What is
Algorithm ?
1. Cormen et al. (2001), Introduction to Algorithms
An algorithm is any well-defined
computational procedure that takes
some value, or set of values, as input
and produces some value, or set of
values as output.[1]
Example: Price monitoring algorithms,
recommendation algorithms, and
price-setting algorithms.
4. What is Bias ?
Presence of any prejudice or favoritism
toward an individual or a group based on their
inherent or acquired characteristics [1].
Example: A search word "nurse" in google
shows picture of women as nurse.
1. Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman and Aram Galstyan. “A
Survey on Bias and Fairness in Machine Learning”, arXiv:1908.09635v2 [cs.LG], 2019.
5. EXAMPLES OF BIASES
• Bias in online forecaster tools to
reoffend [1]
1. Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016.
Machine Bias: There’s software used across the country to predict
future criminals. And it’s biased against blacks. ProPublica 2016.
6. Algorithmic
Bias
[1]Ricardo Baeza-Yates. 2018. Bias on the Web. Commun. ACM 61, 6 (May 2018), 54–61. https://doi.org/10.1145/3209581
Algorithmic bias is when the
bias is not present in the
input data and is added
purely by the algorithm [1].
Example : Price-fixing
algorithm, Biased robo-seller
algorithm
7. Categories of Algorithmic Bias
• Explicit coordination bias:
• Messenger
• Hub and Spoke
• Implicit coordination bias:
• Predictive Agents (Tacit Collusion on
Steroid).
• Artificial Intelligence and Digital Eye
8. Messenger
- Humans agree to collude by
fixing the optimization
algorithm for their competing
products and use algorithms
to facilitate their collusion.
Categories of Algorithmic Bias
Fig. : Explicit coordination implemented or facilitated by algorithms [1]
1. CMA. Pricing Algorithms. October 2018. Available at https://www.icsa.org.uk/knowledge/governance-and-compliance/indepth/technical/pricing-algorithms
9. Messenger Model Example
Poster Cartel:
David Topkins and his co-conspirators
(Trol Ltd. In U.K.) adopted specific pricing
algorithms that collected competitors’
pricing information, with the goal of
coordinating changes to their pricing
strategies for the sale of posters on
Amazon Marketplace [1].
Fig. : Using different kind and sources of data to find the prices that improve
profits [2].
1. Michal S. Gal. Illegal pricing algorithms. Commun. ACM 62, 1 (December 2018), 18–20. DOI: https://doi.org/10.1145/3292515
2. Javier Couto. How Machine Learning is reshaping Price Optimization. 2018. Available at https://tryolabs.com/blog/price-optimization-machine-learning/
Categories of Algorithmic Bias
10. Hub and Spoke
• Same algorithm or data pool
Categories of Algorithmic Bias
1. CMA. Pricing Algorithms. October 2018. Available at https://www.icsa.org.uk/knowledge/governance-and-compliance/indepth/technical/pricing-algorithms
2.Sam Schechner, Why Do Gas Station Prices Constantly Change? Blame the Algorithm, WALL ST. J. (May 8, 2017), https://www.wsj.com/articles/why-do-gas-station-prices-constantly-changeblame-
the-algorithm-1494262674 [https://perma.cc/UR8H-KX8E].
• Common intermediary [2]
Fig. : Tacit coordination due to common pricing algorithms [1]. Fig. : Tacit coordination due to common intermediary [1].
11. Hub and Spoke Model Example
Fig. : Eturas hub-and-spoke using one hub [1] Fig. : Hub-and-spoke using same third-party algorithm [2]
1.Steptoe & Johnson LLP. Cartel Liability in the Online Space Requires More Than a Sent E-mail. 2016. Available at https://www.steptoe.com/en/news-publications/cartel-liability-in-the-online-space-requires-more-than-a-sent-e-mail.html
2.Sam Schechner, Why Do Gas Station Prices Constantly Change? Blame the Algorithm, WALL ST. J. (May 8, 2017), https://www.wsj.com/articles/why-do-gas-station-prices-constantly-changeblame-the-algorithm-1494262674 [https://perma.cc/UR8H-KX8E].
Categories of Algorithmic Bias
12. Predictive Agents
– where humans program their
optimization algorithms to
monitor and respond to rivals’
outcome (e.g. pricing) and other
keys terms of sale, and they
know that the likely outcome
will be conscious parallelism and
higher gain (e.g. gain in prices).
"Conscious Parallelism"
Categories of Algorithmic Bias
Fig. : Process of defining prices in retail with price optimization using
Machine Learning [1].
1. Javier Couto. How Machine Learning is reshaping Price Optimization. 2018. Available at https://tryolabs.com/blog/price-optimization-machine-learning/
13. Predictive Agents Model
1. Freshfields Bruckhaus Deringer LLP, “Pricing algorithms: the digital collusion scenarios”. 2017. Available at https://www.freshfields.com/digital/
2.Competition and Markets Authority (2016), CMA issues final decision in online cartel case. Available at https://www.gov.uk/government/news/cma-issues-final-decision-in-online-cartel-case
Fig. : Tacit coordination without agreement
between rival companies [1].
Fig. : Tacit coordination without agreement between firm and
algorithms but responding fast with the market change [2].
Categories of Algorithmic Bias
14. Predictive Agents Model Scenario
Company
A
Collect
Price
pb
Set Price
pa = pb
Company
B
Collect
Price
pa
Set Price
pb = pa *
80%
Fig. : Company A collects Company B's price and sets its own price to match Company B. Company B also collects Company A's
price and sets its price 20% less [1].
1. Lee, Kenji, Algorithmic Collusion & Its Implications for Competition Law and Policy (April 12, 2018). Available at SSRN: https://ssrn.com/abstract=3213296 or http://dx.doi.org/10.2139/ssrn.3213296
Categories of Algorithmic Bias
15. Predictive Agents Model Example
Tacit collusion on Steroid result = $23,698,655.93
1. Michael Eisen. Amazon’s $23,698,655.93 book about flies. Available at https://blogs.berkeley.edu/2011/04/26/amazon%E2%80%99s-23698655-93-book-about-flies/
Fig. : The price of a biology textbook on Amazon Marketplace in 2011 [1]
Categories of Algorithmic Bias
Fig. : Pattern of price changes for the biology textbook on Amazon
Marketplace in 2011 [1]
16. Artificial Intelligence and the Digital Eye
Under the right market conditions, the self-learning algorithms
may independently arrive at tacit collusion, without the
knowledge or intent of their human programmers.
Categories of Algorithmic Bias
17. Digital Eye Model
‘Win-Continue Lose-Reverse’ rule
Fig. : Reinforcement/Automated learning
between intelligent machine [2].
1. David Silver, Thomas Hubert, Julian Schrittwieser, nIoannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy P. Lillicrap, Karen Simonyan,
Demis Hassabis.Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. CoRR. 2017.
2. Freshfields Bruckhaus Deringer LLP, “Pricing algorithms: the digital collusion scenarios”. 2017. Available at https://www.freshfields.com/digital/
Categories of Algorithmic Bias
Fig. : AlphaZero by Google playing chess game using reinforcement learning [1]
18. Digital Eye Model
Example
Constraint: Trade-off "Higher price
and lower sale"
Goal : Meeting sales target/ specific
share of "Buy Box" Sale
Algorithm : Automated re-pricer
Data : Amazon seller’s past
pricing/profit/revenue data,
competing firms’ prices, and market
information [2]. Fig: Automated repricer algorithm outmaneuvering competitors [1,2]
1.Alexander Galkin. Marketplace Pricing or All You Must Know on Amazon Repricer; How to use Amazon repricer and why do you need it now? Available
at https://competera.net/resources/articles/amazon-repricer
2. Monica Axinte. Quick Introduction to Amazon Pricing Strategies. Available at https://www.datafeedwatch.com/blog/quick-introduction-to-amazon-pricing-strategies
Categories of Algorithmic Bias
19. Explainable AI
Fig. : LIME model explains the symptoms that in the patient ‘s history that led to
the prediction “flu “. Model explains that sneeze and headache are used as
contributing factor for the prediction and no fatigue was used against it. This
explanation helps doctor to trust the model’s prediction [1].
Local Interpretable Model-
agnostic Explanations
(LIME)[1] :
1. Marco Tulio Ribeiro,Sameer Singh, Carlos Guestrin, "Why Should I Trust You?": Explaining the Predictions of Any Classifier, CoRR, 2018
20. Figure : Explaining a prediction of classifiers to determine the class “Christianity” or “Atheism” based on text in documents.
The bar chart showing the importance on the words which determine the prediction. And highlighted in the document. Blue
color indicate “Atheism” and orange indicates “Christianity” [1].
1. Marco Tulio Ribeiro,Sameer Singh, Carlos Guestrin, "Why Should I Trust You?": Explaining the Predictions of Any Classifier, CoRR, 2018
Explainable AI
21. Case
Study
• Demonstrate biasness in competitive decision-making
through algorithmic search and optimization.
• Related to marketplace situation and biasness.
• Addressing ground for information hiding or tacit collusion.
22. Case
Study
Searching for an item for purchase online is a coverage
problem where the search engine should check all
feasible items (S) in query category (Q) to provide
competitive solutions. Accordingly, the goal of a coverage
problem is usually to find a set of points in S which
together minimizes some function or satisfy some other
properties. The objective function
𝑄 ∶ 𝑃 𝑆 → 𝑅
Assume the search problem is an optimization problem,
in case of global optima (minima or maxima)
𝑥∗ ⟺ 𝑠∗ ⟺ 𝑓 𝑥 = min
𝑥 ∈𝑠
𝑓(𝑥)
23. Case Study 1: Detecting bias by Explaining the black box
• Address optimization problem : Travelling Salesman problem, Shortest distance, etc.
• USA highway road network (S): 128 nodes (cities), and each edge (undirected) length less or equal 700 miles.
• The dataset has been collected from Stanford Graphbase database known as "Knuth miles data".
• Goal, f(x) : to find optimal (less travelled path) route (x) to reach destination.
Fig. : Search Space (population space) visualization
24. • A search (Q) from San Jose, CA (start node) to Tampa, FL (stop node).
• Total distance , value[f(x)] = 3049 miles ( A same search in google map provides 2797 miles)
• Route, x = : [ San Jose, CA => San Bernardino, CA => Tucson, AZ => Roswell, NM => Waco, TX =>
Vicksburg, MS => Valdosta, GA => Tampa, FL ]
Case Study 1: Detecting bias by Explaining the black box
Fig. : An instance of optimal class visualization
25. Unbiased: [ San Jose, CA => San Bernardino, CA => Tucson, AZ => Roswell, NM => Waco, TX => Vicksburg, MS
=> Valdosta, GA => Tampa, FL ]
Biased: [ San Jose, CA => San Bernardino, CA => Tucson, AZ => Roswell, NM => Wichita, MS => Saint Louis,
MO=> Tuscalosa, AL => Tampa, FL ]
Case Study 1: Detecting bias by Explaining the black box
26. Case Study 1:
Detecting bias
by Explaining
the black box
Disclosing Information about choices:
• Shortest distance for a search. For
example: 3049 miles
• Distance through some attraction points.
• Distance through using interstate
• Distance through covering maximum
number of gas station. For example: 3478
miles
27. Case Study 2: Detecting bias based on node coverage rate
Problem Definition:
Maximize 𝑖=1
𝑛
𝑣𝑖 𝑥𝑖
Subject to 𝑖=1
𝑛
𝑤𝑖 𝑥𝑖 ≤ 𝑊
Where 𝑣𝑖 is the value of item 𝑖, 𝑤𝑖 is the weight
of item 𝑖, and 𝑥𝑖 ∈ {0,1}
Knapsack 0/1 Test Case:
value = [4,2,10] and weight = [8,1,4], Total capacity W = 10
Unbiased result = 2+10=12
Biased result = 4+2=6
66% node coverage rate.
Fig. : Knapsack 0/1 Problem
28. Case Study 2: Detecting bias based on node coverage rate
Techniques Number
of nodes
Number of
iterations
Average
node
coverage
Optimal
node
coverage
Optimal
value/gain
Genetic Algorithm 100 200 57% 59% 15278
Hill Climbing with
random walk
100 200 55% 57% 17802
Simulated Annealing 100 200 59% 60% 15485
Tabu Search 100 200 47% 54% 17607
Table : Sample Result of four algorithms, ran for 100 nodes dataset
29. Case Study 2: Detecting bias based on node coverage rate
Fig. : Scatter plot of optimal node coverage of unbiased algorithm with increasing number of nodes. Every datapoint in y-axis
represent values identified by each algorithm by their color.
30. Case Study 2: Detecting bias based on node coverage rate
Fig. : Regression plot of optimal node coverage of unbiased algorithm
with increasing number of nodes. Every datapoint in y-axis represent
values identified by each algorithm.
Fig. : Regression plot of optimal node coverage of biased algorithm
against increasing number of nodes. Every datapoint in y-axis
represent values identified by each algorithm.
31. Case Study 2: Detecting bias based on node coverage rate
Fig. : Differences of node coverage rate for biased and unbiased algorithm. Y-axis represent absolute node coverage rate difference with
increasing number of nodes in x-axis.
32. Case Study 2:
Detecting bias
based on node
coverage rate
Disclosing information about node coverage:
• Number of sites visited.
• Number of node covered.
• Explanation for less item coverage.
33. Conclusion
1. Algorithm bias is sometimes intentional, but
sometimes happens inadvertently (especially for
reinforcement learning case).
2. Enforcement laws claim people are equally
responsible for their algorithm/machine's action.
3. Trust and ethics in algorithm/machine are a
debatable issue.
4. To gain trust from consumer explainability of
intelligent system is necessary.
5. From programmer point of view, practice of
explainable AI works as sanity check for software
This category serves as a reminder that price fixing cartels are illegal, irrespective of the means by
which they are implemented or operated. This is the digital equivalent of the smoke-filled room
agreement: algorithms are used intentionally to implement, monitor and police cartels. In this
scenario, humans agree to collude and machines execute the collusion, acting as mere intermediaries
or messengers.
An example is the so-called Poster Cartel case, which made David Topkins, the founder of Poster
Revolution, the first senior manager from an e-commerce business to be prosecuted under antitrust
law by the US Department of Justice. David Topkins and his co-conspirators adopted specific pricing
algorithms that collected competitors’ pricing information, with the goal of coordinating changes to
their pricing strategies for the sale of posters on Amazon Marketplace.
From a legal perspective, the use of algorithms to help execute the cartel’s task has the same effect as
a cartel executed by humans: humans are guilty for agreeing to fix prices, while the computer merely
facilitates the task which humans would otherwise have carried out. Or as Vestager put it: ‘companies
can’t escape responsibility by hiding behind a computer program.’
From a practical perspective, users of pricing algorithms should be aware that sharing information
about the algorithm itself (its structure, workings etc.) publicly or with competitors might be
considered illegal as it would allow others to draw conclusions about how prices are/will be
calculated. In that sense, the algorithm could function as a ‘messenger’ of competitively sensitive
information. Companies will have to be careful to avoid information about their algorithms leaking.
Even if it can be shown that the leak was inadvertent, competition authorities might require
companies to amend their algorithms or adopt new ones in order to prevent collusive behaviour from
arising as a result of the leak.
Current state-of-the-art techniques in price optimization allow retailers to consider factors such as:
Competition
Weather
Season
Operating costs
Local demand
Company objectives
to determine:
The initial price
The best price
The discount price
The promotional price
Price optimization vs dynamic pricing
It is important to differentiate price optimization from dynamic pricing, given that these terms are sometimes used as synonyms. The main difference is that dynamic pricing is a particular pricing strategy, while price optimization can use any kind of pricing strategy to reach its goals. Despite having many advantages and being quite used, dynamic pricing has some disadvantages when used in an extreme way.
Simply put, using a dynamic pricing strategy, retailers can dynamically alter the prices of their products based on current market demand. In contrast, price optimization techniques consider many more factors to suggest a price or a price range for different scenarios (e.g. initial price, best price, discount price, etc.).
We all know and somehow accept because it seems reasonable, that the price of a hotel room or a plane ticket varies according to the season, the day of the week or the anticipation with which we booked. However, when prices change too fast – sometimes in the course of a few hours – some customers might have the feeling that prices are unfair or that the company is practicing price gouging. Dynamic pricing is, therefore, a strategy to be used with caution.
If multiple competitors use the same pricing algorithm, this may lead the
competitors to react in a similar way to external events, such as changes in
input costs or demand. Furthermore, if the competitors are aware or able to
infer that they are using the same or similar pricing algorithms, firms would be
better able to predict their competitors’ responses to price changes, and this
might help firms to better interpret the logic or intention behind competitors’
price setting behaviour. Widespread knowledge and use of common pricing
algorithms may therefore have a similar effect to information exchange in
reducing strategic uncertainty, which may help sustain (but not necessarily
lead to) a tacitly coordinated outcome.
Online retailers using third party provider’s algorithms might find themselves facing cartel
allegations without, in fact, having intended participation in a cartel. In this scenario, various
industry players (the spokes) use the same third-party provider’s (the hub’s) pricing algorithm to
determine the market price and/or react to market changes. Unlike in the first scenario, the
algorithm is not necessarily merely a means to carry out a cartel, but it is the use of the same pricing
algorithm by competitors to monitor prices that leads to the (possibly unintentional) fixing of prices.
The recent Eturas case serves as a reminder that hub-and-spoke agreements also exist in the online
world. Here, the administrator of a Lithuanian online travel booking system sent an electronic notice
to its travel agents, declaring a new technical restriction that put a cap on discount rates. The Court of
Justice of the European Union made clear that travel agents who knew of the message could be
presumed to have participated in a cartel, unless they publicly distanced themselves from the
message. The Court confirmed that actual knowledge of the administrator message was required for
an infringement to exist, but knowledge could be inferred from ‘objective and consistent’ indicia.
Thus, where firms independently sign up to using a platform’s algorithm, knowing that other
competitors are using the same algorithm and that the algorithm fixes prices at a certain level, they
can be held to have engaged in classic hub-and-spoke behaviour.
In light of the Eturas judgment, businesses using third party algorithms will need to ensure online
communication channels (emails, amendments to terms and conditions etc) are effectively monitored
to avoid inferences of collusion (eg where a jointly used algorithm starts setting prices for all of its
users). The precise scope of the ‘objective and consistent’ indicia remains unclear. Deliberately
turning a blind eye is therefore not recommended. Developers of algorithms should also be wary of
the effects of their algorithms, so as to steer clear of allegations of engaging in vertical or facilitating
horizontal collusion.
The recent Eturas case serves as a reminder that hub-and-spoke agreements also exist in the online
world. Here, the administrator of a Lithuanian online travel booking system sent an electronic notice
to its travel agents, declaring a new technical restriction that put a cap on discount rates. The Court of Justice of the European Union made clear that travel agents who knew of the message could be
presumed to have participated in a cartel, unless they publicly distanced themselves from the
message. The Court confirmed that actual knowledge of the administrator message was required for
an infringement to exist, but knowledge could be inferred from ‘objective and consistent’ indicia.Thus, where firms independently sign up to using a platform’s algorithm, knowing that other
competitors are using the same algorithm and that the algorithm fixes prices at a certain level, they
can be held to have engaged in classic hub-and-spoke behaviour
Between 2007 and 2012, 700 petrol stations (which accounted for 25% of the Danish retail fuel market) used a2i pricing algorithm.
5% higher margins = millions of euros
This scenario works on the assumption that the increasing use of pricing algorithms combined with
growing market transparency results in tacit collusion. Under current rules, the tacit collusion
scenario (ie ‘conscious parallelism’ which establishes itself without a need to collude actively) does
not lead to an antitrust offence being committed, so companies do not have to worry about it just yet.
Nevertheless, regulators are already discussing this and it is important that businesses are aware of
the issues, so as to be able to engage actively with regulators, where possible, and be prepared for
and/or influence developments in this area.
Dynamic algorithmic pricing is efficient and clearly yields a competitive advantage, which fewer
companies will want to or can miss out on. With more and more companies adopting pricing
algorithms and more sellers posting their current prices, more market data becomes accessible and
market transparency increases. A market where all firms unilaterally adopt their own pricing
algorithm, accessing their rivals’ real-time pricing and adjusting to each other’s prices within seconds
or even in real time can constitute a breeding ground for tacit collusion. If one firm increases prices,
its rivals’ systems will respond immediately. This normally happens without the risk that enough
customers will realise and be able to move to other sellers. On the flip side, where a firm decreases its
prices, competitors will also adjust theirs straightaway, so that, ultimately, there is no competitive
gain in and hence no incentive to offer discounts.
The risk then arises that market players find a sustainable ‘supra-competitive’ price equilibrium (ie
an algorithm-determined price which is higher than the price that would exist under competitive
market conditions).
Importantly, monitoring your competitors’ prices and reacting to any competitor’s price change
(conscious parallelism), is not in itself unlawful. Thus, whilst real-time monitoring of competitor
prices and dynamic algorithmic pricing might have an anticompetitive effect, absent evidence of any
form of agreement or explicit collusion among competitors, competition agencies – at least as things
currently stand – lack the legal basis for intervention. As put by the German and French authorities
in their joint report: ‘…prosecuting such conducts could prove difficult: first, market transparency is
generally said to benefit consumers when they have – at least in theory – the same information as the
companies and second, no coordination may be necessary to achieve […] supra-competitive results.’
Some commentators have suggested that legislation targeting ‘abuse’ of excessive market
transparency is conceivable. Alternatively, authorities might try and address the issue by preventing
the creation of an excessively transparent market, in the same vein as existing competition law
prohibits mergers that make tacit collusion more likely.
However, arguably, any attempts at prohibiting conscious parallelism or (excessive) market
transparency are likely to raise more questions than they answer. How should the threshold for
intervention be defined? There is general agreement that transparency is in principle pro-competitive
in that it allows consumers to easily compare competing offers, unless the market becomes so
transparent that it ‘tips’ into tacit collusion. It would be very difficult, or even impossible, for any
regulator to reliably predict this ‘tipping point’. Moreover, what would be the remedy in markets
which are classified as susceptible to a risk of tacit collusion? Can the use of pricing algorithms in
certain markets be banned altogether, depriving consumers of the many benefits that these
algorithms entail?
Tacit collusion, sometimes called oligopolistic price coordination or conscious
parallelism, describes the process, not in itself unlawful, by which firms in a
concentrated market might in effect share monopoly power, setting their
prices at a profit-maximizing, supracompetitive level by recognizing their
shared economic interests and their interdependence with respect to price and output decisions.
algorithmic tacit collusion likely would arise in concentrated
markets involving homogenous products where the algorithms can monitor,
to a sufficient degree, the competitors’ pricing, other keys terms of sale,
and any deviations from the current equilibrium.28 Software may be used to
report and take independent action when faced with a rival’s deviation, be
it from the supra-competitive or recommended retail price. Conscious
parallelism would be facilitated and stabilized to the extent (i) these the
rivals’ reactions are predictable, or (ii) through repeated interactions, the
firms’ pricing algorithms “could come to ‘decode’ each other, thus
allowing each one to better anticipate the other’s reaction.”29 As the OECD
observed
An example is what happened to the price of the book “The Making of a Fly”
on Amazon in 2011. This textbook on developmental biology reached a peak
price of $23 million. This price was the result of two sellers’ pricing algorithms.
The first algorithm automatically set the price of the first seller for 1.27059
times the price of the second seller. The second algorithm automatically set
the price of the second seller at 0.9983 times the price of the first seller. This
resulted in the price spiralling upwards until one of the sellers spotted the
mistake and repriced their offer to $106.23.4 This example appears to have
been the result of a lack of “sanity checks” within the algorithms, rather than
any anti-competitive intent. However, it demonstrates how the lack of human
intervention in algorithmic pricing may lead to unintended results.
3 See Amazon’s Match Low Price Help Page.
4 This is detailed in a 2011 blog post by Michael Eisen, Amazon’s $23,698,655.93 book about flies.
What happens if algorithms figure out ways to coordinate prices without their developers / users
being aware of it? That is the question central to this third category in which Artificial Intelligence (ie
the increasing ability of algorithms to make autonomous decisions and learn through experience)
leads to an anticompetitive outcome with no anticompetitive intent or meeting of minds between
humans at all.
Where algorithms are programmed to communicate and exchange information with competitors’
algorithms, it is likely that they will be treated as an extension of human will. Even though the
‘meeting of minds’ takes place at machine level, it was, arguably, initiated at the human level.
Another question is how situations should be treated where the exchange of information between
algorithms was not part of a human plan, but the programmers have (unintentionally) omitted to
implement the necessary safeguards to prevent the exchange from happening. Commissioner
Vestager alludes to this when she states that ‘what businesses can and must do is to ensure antitrust
compliance by design. That means pricing algorithms need to be built in a way that doesn’t allow
them to collude.’
Vestager’s comment suggests that authorities may challenge instances where companies have failed
to build in sufficient safeguards into their algorithms to prevent them from engaging in illegal activity
by ‘agreeing’ with rival firms’ systems to fix prices.
It may indeed be possible to command an algorithm not to fix prices, but what if through selflearning and experimenting with different solutions, including legal forms of coordinated interaction,
the algorithm in its quest to optimise profit finds that the best strategy would be to coordinate prices
regardless? Here, it is machine self-learning that leads to collusion, while the humans that have
programmed or are operating the machines are not aware whether, when or for how long the
collusion has been going on.
Vestager’s reaction is as follows: ‘what businesses need to know is that when they decide to use an
automated system, they will be held responsible for what it does. So they had better know how that
system works.’ But to what extent can humans really be held responsible for their algorithms’ actions
which they maybe knew was one of many possibilities, but certainly not probable? Or as the UK
CMA’s top official David Currie put it: ‘how far can the concept of human agency be stretched to cover
these sorts of issues?’
The general principle under EU law is that companies will be held liable for any anti-competitive
practices of their employees, even if they can show that they have used their best efforts to prevent
such behaviour (eg by implementing a state of the art compliance program). Vestager’s statements
suggest that this principle will be extended to algorithms: where a company uses algorithms to set
prices, it is responsible for any resulting competition risks and will be held strictly liable.
Whilst the idea of algorithms getting together and colluding may still sound like science fiction,
businesses need to be aware that they may be held responsible for whatever the algorithms they
develop or use do. Companies should start thinking about the practical implications of this and the
technical ways in which to prevent M2M collusion from happening.
Here, competitors
unilaterally design an algorithm to reach a pre-set target, such as the
maximisation of profit. If the algorithm is sufficiently complex, it can learn by
itself and experiment with the optimal pricing strategy. There is the possibility
that the algorithms may find the optimal strategy is to enhance market
transparency and tacitly collude. The important difference with the Predictable
Agent model is that the algorithm is not explicitly designed to tacitly collude,
but does so itself through self-learning. It is similar to the Predictable Agent
model in that it would appear difficult to categorise this as falling within Article
101. The algorithms are not just sustaining existing coordination but
generating this coordination themselves.
We are beginning to see Wall Street firms shift from simpler,
programmed algorithms to machine-learning algorithms that pick the
optimal trading strategy. As The Economist observed in 2019:
An early and simple machine learning algorithm developed to set prices is a
‘Win-Continue Lose-Reverse’ rule, and it commonly serves as a benchmark
against which other more sophisticated algorithms are tested. This adaptive
algorithm adjusts prices incrementally in one direction and evaluates what
happens to revenue. If revenue increases, it continues to make similar
changes to price. If not, it makes an incremental change in the opposite
direction. The algorithm make small changes to price in order to learn about
market demand, and requires very limited computational resources and no
data at all on customers.6
Some companies that sell repricing algorithms claim to use machine learning
techniques to improve on simple re-pricing rules. One example of this is an
Amazon marketplace algorithmic re-pricer which the CMA contacted (although
it is not clear whether they are using a neural network).11 The firm providing
pricing services claims to use the Amazon seller’s past pricing/profit/revenue
data, competing firms’ prices, and market information such as competitors’
stock levels, to determine the optimal price to charge consumers. Its algorithm
also takes into account competitors’ publicly-available pricing information and
customer feedback. Whereas simple re-pricers often charge the lowest price
amongst competitors, this machine learning re-pricer maximises profits
through optimising the trade-off between higher prices and lower sales. It
adapts to specific business goals such as meeting sales targets, or capturing
a specific share of the ‘Buy Box’ sales (which is the ‘default’ seller for a
product on Amazon).1