What do you think?
Rate this book
Fairness and Machine Learning: Limitations and Opportunities
An introduction to the intellectual foundations and practical utility of the recent work on fairness and machine learning.
Fairness and Machine Learning introduces advanced undergraduate and graduate students to the intellectual foundations of this recently emergent field, drawing on a diverse range of disciplinary perspectives to identify the opportunities and hazards of automated decision-making. It surveys the risks in many applications of machine learning and provides a review of an emerging set of proposed solutions, showing how even well-intentioned applications may give rise to objectionable results. It covers the statistical and causal measures used to evaluate the fairness of machine learning models as well as the procedural and substantive aspects of decision-making that are core to debates about fairness, including a review of legal and philosophical perspectives on discrimination. This incisive textbook prepares students of machine learning to do quantitative work on fairness while reflecting critically on its foundations and its practical utility.
• Introduces the technical and normative foundations of fairness in automated decision-making
• Covers the formal and computational methods for characterizing and addressing problems
• Provides a critical assessment of their intellectual foundations and practical utility
• Features rich pedagogy and extensive instructor resources
Fairness and Machine Learning introduces advanced undergraduate and graduate students to the intellectual foundations of this recently emergent field, drawing on a diverse range of disciplinary perspectives to identify the opportunities and hazards of automated decision-making. It surveys the risks in many applications of machine learning and provides a review of an emerging set of proposed solutions, showing how even well-intentioned applications may give rise to objectionable results. It covers the statistical and causal measures used to evaluate the fairness of machine learning models as well as the procedural and substantive aspects of decision-making that are core to debates about fairness, including a review of legal and philosophical perspectives on discrimination. This incisive textbook prepares students of machine learning to do quantitative work on fairness while reflecting critically on its foundations and its practical utility.
• Introduces the technical and normative foundations of fairness in automated decision-making
• Covers the formal and computational methods for characterizing and addressing problems
• Provides a critical assessment of their intellectual foundations and practical utility
• Features rich pedagogy and extensive instructor resources
329 pages, Kindle Edition
Published December 19, 2023
8 people are currently reading
95 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 2 of 2 reviews
February 14, 2025
The best thing of this book is it is open-source. Everyone can read it online at https://fairmlbook.org/
It discussed social fairness, how people tried to mitigate bias in the past and now, and how people put effort to improve fairness in technology in machine learning.
No a math heavy book -- Only Ch3 and Ch5 need some math backgrounds.
Started from technique side of machine learning and math theory, authors extend fairness to its history, real-world application, given a big picture of the topic. I like Chapter Notes which provided other further reading for interests.
High-level take away for me:
1. I like the idea to pair philosophy of equity with the stat criteria in Ch4. -- tho it need sometime to digest and I, currently, almost forgot what they said.
2. Some features other than the protected one may explain the outcome, but that does not mean there is no discrimination. It is possible that social expectation or other structural discrimination lead to those feature disparities. In short, pay attention to the structural discrimination in the society (Uber analysis in Ch7)
3. Try not to only focus on disparity criteria. (from Ch8)
It also let me think, what is fairness, what is justice -- if protecting minority group means we need to trade off some efficiency of the group how should we balance between these two.
Still, I was thinking, most of times when a decision gets made, there will always be someone got hurt, some one got benefit. Those who have more power and at a higher social hierarchy position always have more sources to legitimate it/to grab it/to occupy it, despite promotion of fairness or justice -- which is a sad story but without solution, at least no solution in my mind.
It discussed social fairness, how people tried to mitigate bias in the past and now, and how people put effort to improve fairness in technology in machine learning.
No a math heavy book -- Only Ch3 and Ch5 need some math backgrounds.
Started from technique side of machine learning and math theory, authors extend fairness to its history, real-world application, given a big picture of the topic. I like Chapter Notes which provided other further reading for interests.
High-level take away for me:
1. I like the idea to pair philosophy of equity with the stat criteria in Ch4. -- tho it need sometime to digest and I, currently, almost forgot what they said.
2. Some features other than the protected one may explain the outcome, but that does not mean there is no discrimination. It is possible that social expectation or other structural discrimination lead to those feature disparities. In short, pay attention to the structural discrimination in the society (Uber analysis in Ch7)
3. Try not to only focus on disparity criteria. (from Ch8)
It also let me think, what is fairness, what is justice -- if protecting minority group means we need to trade off some efficiency of the group how should we balance between these two.
Still, I was thinking, most of times when a decision gets made, there will always be someone got hurt, some one got benefit. Those who have more power and at a higher social hierarchy position always have more sources to legitimate it/to grab it/to occupy it, despite promotion of fairness or justice -- which is a sad story but without solution, at least no solution in my mind.
January 28, 2026
Read in the context of my PhD on fairness in XAI. In addition to an overview of the existing literature and relevant definitions, the book seems to also provide the necessary background to ask the right (high-level) fairness questions on everything ML related.
I however missed a chapter on internationally relevant legislature concerning fairness issues in ML (GDPR, AI Act), given the scope was (as is often the case with American authors) completely US-centered.
Strongly recommend if you’re new to the field of fairness in ML; 4/5
I however missed a chapter on internationally relevant legislature concerning fairness issues in ML (GDPR, AI Act), given the scope was (as is often the case with American authors) completely US-centered.
Strongly recommend if you’re new to the field of fairness in ML; 4/5
Displaying 1 - 2 of 2 reviews