Fairness and machine learning: limitations and opportunities
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Cambridge ; London
The MIT Press
[2023]
|
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis |
| Beschreibung: | 40 BLACK AND WHITE ILLUS. |
| Beschreibung: | xiv, 323 Seiten Diagramme 229 mm |
| ISBN: | 9780262048613 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV049467215 | ||
| 003 | DE-604 | ||
| 005 | 20240603 | ||
| 007 | t | ||
| 008 | 231214s2023 |||| |||| 00||| eng d | ||
| 020 | |a 9780262048613 |c hbk |9 978-0-262-04861-3 | ||
| 035 | |a (OCoLC)1420510919 | ||
| 035 | |a (DE-599)BVBBV049467215 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-473 |a DE-2070s |a DE-M468 |a DE-739 | ||
| 084 | |a SR 850 |0 (DE-625)143366: |2 rvk | ||
| 084 | |a MS 4800 |0 (DE-625)123718: |2 rvk | ||
| 100 | 1 | |a Barocas, Solon |e Verfasser |0 (DE-588)1314323296 |4 aut | |
| 245 | 1 | 0 | |a Fairness and machine learning |b limitations and opportunities |c Solon Barocas, Moritz Hardt and Arvind Narayanan |
| 264 | 1 | |a Cambridge ; London |b The MIT Press |c [2023] | |
| 264 | 4 | |c © 2023 | |
| 300 | |a xiv, 323 Seiten |b Diagramme |c 229 mm | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a 40 BLACK AND WHITE ILLUS. | ||
| 650 | 4 | |a bisacsh / COMPUTERS / Artificial Intelligence / General | |
| 650 | 4 | |a bisacsh / TECHNOLOGY & ENGINEERING / Social Aspects | |
| 650 | 4 | |a Discrimination - Law and legislation - United States | |
| 650 | 4 | |a Decision making - Moral and ethical aspects - United States | |
| 650 | 4 | |a Machine learning - Moral and ethical aspects - United States | |
| 650 | 4 | |a Automation - Human factors - United States | |
| 650 | 0 | 7 | |a Gerechtigkeit |0 (DE-588)4020310-4 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4123623-3 |a Lehrbuch |2 gnd-content | |
| 689 | 0 | 0 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | 1 | |a Gerechtigkeit |0 (DE-588)4020310-4 |D s |
| 689 | 0 | |5 DE-604 | |
| 700 | 1 | |a Hardt, Moritz |e Verfasser |0 (DE-588)1281863343 |4 aut | |
| 700 | 1 | |a Narayanan, Arvind |e Verfasser |0 (DE-588)1129195163 |4 aut | |
| 856 | 4 | 2 | |m Digitalisierung UB Bamberg - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034812865&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
Datensatz im Suchindex
| _version_ | 1805083773745758208 |
|---|---|
| adam_text |
Contents Preface ix Online Materials xiv Acknowledgments 1 Introduction xv 1 Demographic Disparities 3 The Machine Learning Loop The State of Society 5 6 The Trouble with Measurement From Data to Models The Pitfalls of Action 8 11 13 Feedback and Feedback Loops 14 17 Getting Concrete with a Toy Example Justice beyond Fair Decision Making 20 Our Outlook: Limitations and Opportunities 22 Bibliographic Notes and Further Reading 23 2 When Is Automated Decision Making Legitimate? 25 Machine Learning Is Not a Replacement for Human Decision Making Bureaucracy as a Bulwark against Arbitrary Decision Making Three Forms of Automation 30 Mismatch between Target and Goal 36 Failing to Consider Relevant Information The Limits of Induction A Right to Accurate Predictions? Agency, Recourse, and Culpability Concluding Thoughts 3 Classification 38 41 43 44 47 49 Modeling Populations as Probability Distributions Formalizing Classification Supervised Learning 51 56 Groups in the Population 58 50 28 26
vi Contents Statistical Nondiscrimination Criteria Independence 61 60 Separation 63 Sufficiency 67 How to Satisfy a Nondiscrimination Criterion Relationships between Criteria 71 Case Study: Credit Scoring 74 Inherent Limitations of Observational Criteria Chapter Notes 80 4 Relative Notions of Fairness 70 79 83 Systematic Relative Disadvantage 83 Six Accounts of the Wrongfulness of Discrimination 85 Intentionality and Indirect Discrimination 87 Equality of Opportunity 88 Tensions between the Different Views 93 Merit and Desert 95 The Cost of Fairness 98 Connecting Statistical and Moral Notions of Fairness 100 The Normative Underpinnings of Error Rate Parity 105 Alternatives for Realizing the Middle View of Equality of Opportunity Summary 110 5 Causality 113 The Limitations of Observation 114 Causal Models 117 Causal Graphs 120 Interventions and Causal Effects 123 Confounding 124 Graphical Discrimination Analysis 127 Counterfactuals 132 Counterfactual Discrimination Analysis Validity of Causal Modeling 143 Chapter Notes 149 6 138 Understanding United States Antidiscrimination Law History and Overview of US Antidiscrimination Law A Few Basics of the American Legal System 157 How the Law Conceives of Discrimination 163 Limits of the Law in Curbing Discrimination 167 Regulating Machine Learning 172 Concluding Thoughts 182 7 Testing Discrimination in Practice 185 Part 1 : Traditional Tests for Discrimination Audit Studies 186 Testing the Impact of Blinding 190 186 152 151 109
Contents vii Revealing Extraneous Factors in Decisions 192 Testing the Impact of Decisions and Interventions Purely Observational Tests 193 194 Taste-Based and Statistical Discrimination 198 Studies of Decision-Making Processes and Organizations Part 2: Testing Discrimination in Algorithmic Systems 200 202 Fairness Considerations in Applications of Natural Language Processing 203 Demographic Disparities and Questionable Applications of Computer Vision Search and Recommendation Systems: Three Types of Harms Understanding Unfairness in Ad Targeting 208 Fairness Considerations in the Design of Online Marketplaces Mechanisms of Discrimination 212 Fairness Criteria in Algorithmic Audits Information Flow, Fairness, Privacy Comparison of Research Methods Looking Ahead 8 214 215 217 219 Chapter Notes 219 A Broader View of Discrimination 221 Case Study: The Gender Earnings Gap on Uber Three Levels of Discrimination 221 225 Machine Learning and Structural Discrimination 229 Structural Interventions for Fair Machine Learning 234 Organizational Interventions for Fairer Decision Making Concluding Thoughts Chapter Notes 245 247 Appendix: A Deeper Look at Structural Factors 9 Datasets 251 A Tour of Datasets in Different Domains Roles Datasets Play 260 Harms Associated with Data Beyond Datasets Summary 282 Chapter Notes References Index 311 274 282 285 271 206 252 248 238 210 204 |
| adam_txt |
Contents Preface ix Online Materials xiv Acknowledgments 1 Introduction xv 1 Demographic Disparities 3 The Machine Learning Loop The State of Society 5 6 The Trouble with Measurement From Data to Models The Pitfalls of Action 8 11 13 Feedback and Feedback Loops 14 17 Getting Concrete with a Toy Example Justice beyond Fair Decision Making 20 Our Outlook: Limitations and Opportunities 22 Bibliographic Notes and Further Reading 23 2 When Is Automated Decision Making Legitimate? 25 Machine Learning Is Not a Replacement for Human Decision Making Bureaucracy as a Bulwark against Arbitrary Decision Making Three Forms of Automation 30 Mismatch between Target and Goal 36 Failing to Consider Relevant Information The Limits of Induction A Right to Accurate Predictions? Agency, Recourse, and Culpability Concluding Thoughts 3 Classification 38 41 43 44 47 49 Modeling Populations as Probability Distributions Formalizing Classification Supervised Learning 51 56 Groups in the Population 58 50 28 26
vi Contents Statistical Nondiscrimination Criteria Independence 61 60 Separation 63 Sufficiency 67 How to Satisfy a Nondiscrimination Criterion Relationships between Criteria 71 Case Study: Credit Scoring 74 Inherent Limitations of Observational Criteria Chapter Notes 80 4 Relative Notions of Fairness 70 79 83 Systematic Relative Disadvantage 83 Six Accounts of the Wrongfulness of Discrimination 85 Intentionality and Indirect Discrimination 87 Equality of Opportunity 88 Tensions between the Different Views 93 Merit and Desert 95 The Cost of Fairness 98 Connecting Statistical and Moral Notions of Fairness 100 The Normative Underpinnings of Error Rate Parity 105 Alternatives for Realizing the Middle View of Equality of Opportunity Summary 110 5 Causality 113 The Limitations of Observation 114 Causal Models 117 Causal Graphs 120 Interventions and Causal Effects 123 Confounding 124 Graphical Discrimination Analysis 127 Counterfactuals 132 Counterfactual Discrimination Analysis Validity of Causal Modeling 143 Chapter Notes 149 6 138 Understanding United States Antidiscrimination Law History and Overview of US Antidiscrimination Law A Few Basics of the American Legal System 157 How the Law Conceives of Discrimination 163 Limits of the Law in Curbing Discrimination 167 Regulating Machine Learning 172 Concluding Thoughts 182 7 Testing Discrimination in Practice 185 Part 1 : Traditional Tests for Discrimination Audit Studies 186 Testing the Impact of Blinding 190 186 152 151 109
Contents vii Revealing Extraneous Factors in Decisions 192 Testing the Impact of Decisions and Interventions Purely Observational Tests 193 194 Taste-Based and Statistical Discrimination 198 Studies of Decision-Making Processes and Organizations Part 2: Testing Discrimination in Algorithmic Systems 200 202 Fairness Considerations in Applications of Natural Language Processing 203 Demographic Disparities and Questionable Applications of Computer Vision Search and Recommendation Systems: Three Types of Harms Understanding Unfairness in Ad Targeting 208 Fairness Considerations in the Design of Online Marketplaces Mechanisms of Discrimination 212 Fairness Criteria in Algorithmic Audits Information Flow, Fairness, Privacy Comparison of Research Methods Looking Ahead 8 214 215 217 219 Chapter Notes 219 A Broader View of Discrimination 221 Case Study: The Gender Earnings Gap on Uber Three Levels of Discrimination 221 225 Machine Learning and Structural Discrimination 229 Structural Interventions for Fair Machine Learning 234 Organizational Interventions for Fairer Decision Making Concluding Thoughts Chapter Notes 245 247 Appendix: A Deeper Look at Structural Factors 9 Datasets 251 A Tour of Datasets in Different Domains Roles Datasets Play 260 Harms Associated with Data Beyond Datasets Summary 282 Chapter Notes References Index 311 274 282 285 271 206 252 248 238 210 204 |
| any_adam_object | 1 |
| any_adam_object_boolean | 1 |
| author | Barocas, Solon Hardt, Moritz Narayanan, Arvind |
| author_GND | (DE-588)1314323296 (DE-588)1281863343 (DE-588)1129195163 |
| author_facet | Barocas, Solon Hardt, Moritz Narayanan, Arvind |
| author_role | aut aut aut |
| author_sort | Barocas, Solon |
| author_variant | s b sb m h mh a n an |
| building | Verbundindex |
| bvnumber | BV049467215 |
| classification_rvk | SR 850 MS 4800 |
| ctrlnum | (OCoLC)1420510919 (DE-599)BVBBV049467215 |
| discipline | Informatik Soziologie |
| discipline_str_mv | Informatik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a2200000 c 4500</leader><controlfield tag="001">BV049467215</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20240603</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">231214s2023 |||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780262048613</subfield><subfield code="c">hbk</subfield><subfield code="9">978-0-262-04861-3</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1420510919</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV049467215</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-473</subfield><subfield code="a">DE-2070s</subfield><subfield code="a">DE-M468</subfield><subfield code="a">DE-739</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">SR 850</subfield><subfield code="0">(DE-625)143366:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">MS 4800</subfield><subfield code="0">(DE-625)123718:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Barocas, Solon</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1314323296</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Fairness and machine learning</subfield><subfield code="b">limitations and opportunities</subfield><subfield code="c">Solon Barocas, Moritz Hardt and Arvind Narayanan</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge ; London</subfield><subfield code="b">The MIT Press</subfield><subfield code="c">[2023]</subfield></datafield><datafield tag="264" ind1=" " ind2="4"><subfield code="c">© 2023</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xiv, 323 Seiten</subfield><subfield code="b">Diagramme</subfield><subfield code="c">229 mm</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">40 BLACK AND WHITE ILLUS.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh / COMPUTERS / Artificial Intelligence / General</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">bisacsh / TECHNOLOGY & ENGINEERING / Social Aspects</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Discrimination - Law and legislation - United States</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Decision making - Moral and ethical aspects - United States</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning - Moral and ethical aspects - United States</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Automation - Human factors - United States</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Gerechtigkeit</subfield><subfield code="0">(DE-588)4020310-4</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4123623-3</subfield><subfield code="a">Lehrbuch</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Gerechtigkeit</subfield><subfield code="0">(DE-588)4020310-4</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hardt, Moritz</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1281863343</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Narayanan, Arvind</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1129195163</subfield><subfield code="4">aut</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Bamberg - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034812865&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield></record></collection> |
| genre | (DE-588)4123623-3 Lehrbuch gnd-content |
| genre_facet | Lehrbuch |
| id | DE-604.BV049467215 |
| illustrated | Not Illustrated |
| index_date | 2024-07-03T23:16:05Z |
| indexdate | 2024-07-20T07:53:53Z |
| institution | BVB |
| isbn | 9780262048613 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-034812865 |
| oclc_num | 1420510919 |
| open_access_boolean | |
| owner | DE-473 DE-BY-UBG DE-2070s DE-M468 DE-739 |
| owner_facet | DE-473 DE-BY-UBG DE-2070s DE-M468 DE-739 |
| physical | xiv, 323 Seiten Diagramme 229 mm |
| publishDate | 2023 |
| publishDateSearch | 2023 |
| publishDateSort | 2023 |
| publisher | The MIT Press |
| record_format | marc |
| spelling | Barocas, Solon Verfasser (DE-588)1314323296 aut Fairness and machine learning limitations and opportunities Solon Barocas, Moritz Hardt and Arvind Narayanan Cambridge ; London The MIT Press [2023] © 2023 xiv, 323 Seiten Diagramme 229 mm txt rdacontent n rdamedia nc rdacarrier 40 BLACK AND WHITE ILLUS. bisacsh / COMPUTERS / Artificial Intelligence / General bisacsh / TECHNOLOGY & ENGINEERING / Social Aspects Discrimination - Law and legislation - United States Decision making - Moral and ethical aspects - United States Machine learning - Moral and ethical aspects - United States Automation - Human factors - United States Gerechtigkeit (DE-588)4020310-4 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf (DE-588)4123623-3 Lehrbuch gnd-content Maschinelles Lernen (DE-588)4193754-5 s Gerechtigkeit (DE-588)4020310-4 s DE-604 Hardt, Moritz Verfasser (DE-588)1281863343 aut Narayanan, Arvind Verfasser (DE-588)1129195163 aut Digitalisierung UB Bamberg - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034812865&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Barocas, Solon Hardt, Moritz Narayanan, Arvind Fairness and machine learning limitations and opportunities bisacsh / COMPUTERS / Artificial Intelligence / General bisacsh / TECHNOLOGY & ENGINEERING / Social Aspects Discrimination - Law and legislation - United States Decision making - Moral and ethical aspects - United States Machine learning - Moral and ethical aspects - United States Automation - Human factors - United States Gerechtigkeit (DE-588)4020310-4 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| subject_GND | (DE-588)4020310-4 (DE-588)4193754-5 (DE-588)4123623-3 |
| title | Fairness and machine learning limitations and opportunities |
| title_auth | Fairness and machine learning limitations and opportunities |
| title_exact_search | Fairness and machine learning limitations and opportunities |
| title_exact_search_txtP | Fairness and machine learning limitations and opportunities |
| title_full | Fairness and machine learning limitations and opportunities Solon Barocas, Moritz Hardt and Arvind Narayanan |
| title_fullStr | Fairness and machine learning limitations and opportunities Solon Barocas, Moritz Hardt and Arvind Narayanan |
| title_full_unstemmed | Fairness and machine learning limitations and opportunities Solon Barocas, Moritz Hardt and Arvind Narayanan |
| title_short | Fairness and machine learning |
| title_sort | fairness and machine learning limitations and opportunities |
| title_sub | limitations and opportunities |
| topic | bisacsh / COMPUTERS / Artificial Intelligence / General bisacsh / TECHNOLOGY & ENGINEERING / Social Aspects Discrimination - Law and legislation - United States Decision making - Moral and ethical aspects - United States Machine learning - Moral and ethical aspects - United States Automation - Human factors - United States Gerechtigkeit (DE-588)4020310-4 gnd Maschinelles Lernen (DE-588)4193754-5 gnd |
| topic_facet | bisacsh / COMPUTERS / Artificial Intelligence / General bisacsh / TECHNOLOGY & ENGINEERING / Social Aspects Discrimination - Law and legislation - United States Decision making - Moral and ethical aspects - United States Machine learning - Moral and ethical aspects - United States Automation - Human factors - United States Gerechtigkeit Maschinelles Lernen Lehrbuch |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034812865&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT barocassolon fairnessandmachinelearninglimitationsandopportunities AT hardtmoritz fairnessandmachinelearninglimitationsandopportunities AT narayananarvind fairnessandmachinelearninglimitationsandopportunities |