Close Modal

Fairness and Machine Learning

Limitations and Opportunities

Look inside
Hardcover
$65.00 US
7.25"W x 9.25"H x 1"D   (18.4 x 23.5 x 2.5 cm) | 27 oz (777 g) | 16 per carton
On sale Dec 19, 2023 | 340 Pages | 9780262048613
Sales rights: World

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
Solon Barocas is a Principal Researcher in the New York City lab of Microsoft Research, where he is a member of the Fairness, Accountability, Transparency, and Ethics in AI (FATE) research group. He is an Adjunct Assistant Professor in the Department of Information Science at Cornell University and Faculty Associate at the Berkman Klein Center for Internet & Society at Harvard University.

Moritz Hardt is Director of Social Foundations of Computation at the Max Planck Institute for Intelligent Systems and coauthor of Patterns, Predictions, and Actions: Foundations of Machine Learning.

Arvind Narayanan is Professor of Computer Science at Princeton University and director of the Center for Information Technology Policy. His work was among the first to show how machine learning reflects cultural stereotypes, and he led the Princeton Web Transparency and Accountability Project to uncover how companies collect and use our personal information.
Available for sale exclusive:
•     Afghanistan
•     Aland Islands
•     Albania
•     Algeria
•     Andorra
•     Angola
•     Anguilla
•     Antarctica
•     Antigua/Barbuda
•     Argentina
•     Armenia
•     Aruba
•     Australia
•     Austria
•     Azerbaijan
•     Bahamas
•     Bahrain
•     Bangladesh
•     Barbados
•     Belarus
•     Belgium
•     Belize
•     Benin
•     Bermuda
•     Bhutan
•     Bolivia
•     Bonaire, Saba
•     Bosnia Herzeg.
•     Botswana
•     Bouvet Island
•     Brazil
•     Brit.Ind.Oc.Ter
•     Brit.Virgin Is.
•     Brunei
•     Bulgaria
•     Burkina Faso
•     Burundi
•     Cambodia
•     Cameroon
•     Canada
•     Cape Verde
•     Cayman Islands
•     Centr.Afr.Rep.
•     Chad
•     Chile
•     China
•     Christmas Islnd
•     Cocos Islands
•     Colombia
•     Comoro Is.
•     Congo
•     Cook Islands
•     Costa Rica
•     Croatia
•     Cuba
•     Curacao
•     Cyprus
•     Czech Republic
•     Dem. Rep. Congo
•     Denmark
•     Djibouti
•     Dominica
•     Dominican Rep.
•     Ecuador
•     Egypt
•     El Salvador
•     Equatorial Gui.
•     Eritrea
•     Estonia
•     Ethiopia
•     Falkland Islnds
•     Faroe Islands
•     Fiji
•     Finland
•     France
•     Fren.Polynesia
•     French Guinea
•     Gabon
•     Gambia
•     Georgia
•     Germany
•     Ghana
•     Gibraltar
•     Greece
•     Greenland
•     Grenada
•     Guadeloupe
•     Guam
•     Guatemala
•     Guernsey
•     Guinea Republic
•     Guinea-Bissau
•     Guyana
•     Haiti
•     Heard/McDon.Isl
•     Honduras
•     Hong Kong
•     Hungary
•     Iceland
•     India
•     Indonesia
•     Iran
•     Iraq
•     Ireland
•     Isle of Man
•     Israel
•     Italy
•     Ivory Coast
•     Jamaica
•     Japan
•     Jersey
•     Jordan
•     Kazakhstan
•     Kenya
•     Kiribati
•     Kuwait
•     Kyrgyzstan
•     Laos
•     Latvia
•     Lebanon
•     Lesotho
•     Liberia
•     Libya
•     Liechtenstein
•     Lithuania
•     Luxembourg
•     Macau
•     Macedonia
•     Madagascar
•     Malawi
•     Malaysia
•     Maldives
•     Mali
•     Malta
•     Marshall island
•     Martinique
•     Mauritania
•     Mauritius
•     Mayotte
•     Mexico
•     Micronesia
•     Minor Outl.Ins.
•     Moldavia
•     Monaco
•     Mongolia
•     Montenegro
•     Montserrat
•     Morocco
•     Mozambique
•     Myanmar
•     Namibia
•     Nauru
•     Nepal
•     Netherlands
•     New Caledonia
•     New Zealand
•     Nicaragua
•     Niger
•     Nigeria
•     Niue
•     Norfolk Island
•     North Korea
•     North Mariana
•     Norway
•     Oman
•     Pakistan
•     Palau
•     Palestinian Ter
•     Panama
•     PapuaNewGuinea
•     Paraguay
•     Peru
•     Philippines
•     Pitcairn Islnds
•     Poland
•     Portugal
•     Puerto Rico
•     Qatar
•     Reunion Island
•     Romania
•     Russian Fed.
•     Rwanda
•     S. Sandwich Ins
•     Saint Martin
•     Samoa,American
•     San Marino
•     SaoTome Princip
•     Saudi Arabia
•     Senegal
•     Serbia
•     Seychelles
•     Sierra Leone
•     Singapore
•     Sint Maarten
•     Slovakia
•     Slovenia
•     Solomon Islands
•     Somalia
•     South Africa
•     South Korea
•     South Sudan
•     Spain
•     Sri Lanka
•     St Barthelemy
•     St. Helena
•     St. Lucia
•     St. Vincent
•     St.Chr.,Nevis
•     St.Pier,Miquel.
•     Sth Terr. Franc
•     Sudan
•     Suriname
•     Svalbard
•     Swaziland
•     Sweden
•     Switzerland
•     Syria
•     Tadschikistan
•     Taiwan
•     Tanzania
•     Thailand
•     Timor-Leste
•     Togo
•     Tokelau Islands
•     Tonga
•     Trinidad,Tobago
•     Tunisia
•     Turkey
•     Turkmenistan
•     Turks&Caicos Is
•     Tuvalu
•     US Virgin Is.
•     USA
•     Uganda
•     Ukraine
•     Unit.Arab Emir.
•     United Kingdom
•     Uruguay
•     Uzbekistan
•     Vanuatu
•     Vatican City
•     Venezuela
•     Vietnam
•     Wallis,Futuna
•     West Saharan
•     Western Samoa
•     Yemen
•     Zambia
•     Zimbabwe

Preface ix
Online Materials xiv
Acknowledgments xv
1 Introduction 1
2 When Is Automated Decision Making Legitimate? 25
3 Classification 49
4 Relative Notions of Fairness 83
5 Causality 113
6 Understanding United States Antidiscrimination Law 151
7 Testing Discrimination in Practice 185
8 A Broader View of Discrimination 221
9 Datasets 251
References 285
Index 311

About

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

Author

Solon Barocas is a Principal Researcher in the New York City lab of Microsoft Research, where he is a member of the Fairness, Accountability, Transparency, and Ethics in AI (FATE) research group. He is an Adjunct Assistant Professor in the Department of Information Science at Cornell University and Faculty Associate at the Berkman Klein Center for Internet & Society at Harvard University.

Moritz Hardt is Director of Social Foundations of Computation at the Max Planck Institute for Intelligent Systems and coauthor of Patterns, Predictions, and Actions: Foundations of Machine Learning.

Arvind Narayanan is Professor of Computer Science at Princeton University and director of the Center for Information Technology Policy. His work was among the first to show how machine learning reflects cultural stereotypes, and he led the Princeton Web Transparency and Accountability Project to uncover how companies collect and use our personal information.

Rights

Available for sale exclusive:
•     Afghanistan
•     Aland Islands
•     Albania
•     Algeria
•     Andorra
•     Angola
•     Anguilla
•     Antarctica
•     Antigua/Barbuda
•     Argentina
•     Armenia
•     Aruba
•     Australia
•     Austria
•     Azerbaijan
•     Bahamas
•     Bahrain
•     Bangladesh
•     Barbados
•     Belarus
•     Belgium
•     Belize
•     Benin
•     Bermuda
•     Bhutan
•     Bolivia
•     Bonaire, Saba
•     Bosnia Herzeg.
•     Botswana
•     Bouvet Island
•     Brazil
•     Brit.Ind.Oc.Ter
•     Brit.Virgin Is.
•     Brunei
•     Bulgaria
•     Burkina Faso
•     Burundi
•     Cambodia
•     Cameroon
•     Canada
•     Cape Verde
•     Cayman Islands
•     Centr.Afr.Rep.
•     Chad
•     Chile
•     China
•     Christmas Islnd
•     Cocos Islands
•     Colombia
•     Comoro Is.
•     Congo
•     Cook Islands
•     Costa Rica
•     Croatia
•     Cuba
•     Curacao
•     Cyprus
•     Czech Republic
•     Dem. Rep. Congo
•     Denmark
•     Djibouti
•     Dominica
•     Dominican Rep.
•     Ecuador
•     Egypt
•     El Salvador
•     Equatorial Gui.
•     Eritrea
•     Estonia
•     Ethiopia
•     Falkland Islnds
•     Faroe Islands
•     Fiji
•     Finland
•     France
•     Fren.Polynesia
•     French Guinea
•     Gabon
•     Gambia
•     Georgia
•     Germany
•     Ghana
•     Gibraltar
•     Greece
•     Greenland
•     Grenada
•     Guadeloupe
•     Guam
•     Guatemala
•     Guernsey
•     Guinea Republic
•     Guinea-Bissau
•     Guyana
•     Haiti
•     Heard/McDon.Isl
•     Honduras
•     Hong Kong
•     Hungary
•     Iceland
•     India
•     Indonesia
•     Iran
•     Iraq
•     Ireland
•     Isle of Man
•     Israel
•     Italy
•     Ivory Coast
•     Jamaica
•     Japan
•     Jersey
•     Jordan
•     Kazakhstan
•     Kenya
•     Kiribati
•     Kuwait
•     Kyrgyzstan
•     Laos
•     Latvia
•     Lebanon
•     Lesotho
•     Liberia
•     Libya
•     Liechtenstein
•     Lithuania
•     Luxembourg
•     Macau
•     Macedonia
•     Madagascar
•     Malawi
•     Malaysia
•     Maldives
•     Mali
•     Malta
•     Marshall island
•     Martinique
•     Mauritania
•     Mauritius
•     Mayotte
•     Mexico
•     Micronesia
•     Minor Outl.Ins.
•     Moldavia
•     Monaco
•     Mongolia
•     Montenegro
•     Montserrat
•     Morocco
•     Mozambique
•     Myanmar
•     Namibia
•     Nauru
•     Nepal
•     Netherlands
•     New Caledonia
•     New Zealand
•     Nicaragua
•     Niger
•     Nigeria
•     Niue
•     Norfolk Island
•     North Korea
•     North Mariana
•     Norway
•     Oman
•     Pakistan
•     Palau
•     Palestinian Ter
•     Panama
•     PapuaNewGuinea
•     Paraguay
•     Peru
•     Philippines
•     Pitcairn Islnds
•     Poland
•     Portugal
•     Puerto Rico
•     Qatar
•     Reunion Island
•     Romania
•     Russian Fed.
•     Rwanda
•     S. Sandwich Ins
•     Saint Martin
•     Samoa,American
•     San Marino
•     SaoTome Princip
•     Saudi Arabia
•     Senegal
•     Serbia
•     Seychelles
•     Sierra Leone
•     Singapore
•     Sint Maarten
•     Slovakia
•     Slovenia
•     Solomon Islands
•     Somalia
•     South Africa
•     South Korea
•     South Sudan
•     Spain
•     Sri Lanka
•     St Barthelemy
•     St. Helena
•     St. Lucia
•     St. Vincent
•     St.Chr.,Nevis
•     St.Pier,Miquel.
•     Sth Terr. Franc
•     Sudan
•     Suriname
•     Svalbard
•     Swaziland
•     Sweden
•     Switzerland
•     Syria
•     Tadschikistan
•     Taiwan
•     Tanzania
•     Thailand
•     Timor-Leste
•     Togo
•     Tokelau Islands
•     Tonga
•     Trinidad,Tobago
•     Tunisia
•     Turkey
•     Turkmenistan
•     Turks&Caicos Is
•     Tuvalu
•     US Virgin Is.
•     USA
•     Uganda
•     Ukraine
•     Unit.Arab Emir.
•     United Kingdom
•     Uruguay
•     Uzbekistan
•     Vanuatu
•     Vatican City
•     Venezuela
•     Vietnam
•     Wallis,Futuna
•     West Saharan
•     Western Samoa
•     Yemen
•     Zambia
•     Zimbabwe

Table of Contents

Preface ix
Online Materials xiv
Acknowledgments xv
1 Introduction 1
2 When Is Automated Decision Making Legitimate? 25
3 Classification 49
4 Relative Notions of Fairness 83
5 Causality 113
6 Understanding United States Antidiscrimination Law 151
7 Testing Discrimination in Practice 185
8 A Broader View of Discrimination 221
9 Datasets 251
References 285
Index 311