M. Pagnucco, D. Rajaratnam, Raynaldio Limarga, Abhaya C. Nayak, Yang Song
With the rapid development of autonomous machines such as selfdriving vehicles and social robots, there is increasing realisation that machine ethics is important for widespread acceptance of autonomous machines. Our objective is to encode ethical reasoning into autonomous machines following well-defined ethical principles and behavioural norms. We provide an approach to reasoning about actions that incorporates ethical considerations. It builds on Scherl and Levesque's [29, 30] approach to knowledge in the situation calculus. We show how reasoning about knowledge in a dynamic setting can be used to guide ethical and moral choices, aligned with consequentialist and deontological approaches to ethics. We apply our approach to autonomous driving and social robot scenarios, and provide an implementation framework.
{"title":"Epistemic Reasoning for Machine Ethics with Situation Calculus","authors":"M. Pagnucco, D. Rajaratnam, Raynaldio Limarga, Abhaya C. Nayak, Yang Song","doi":"10.1145/3461702.3462586","DOIUrl":"https://doi.org/10.1145/3461702.3462586","url":null,"abstract":"With the rapid development of autonomous machines such as selfdriving vehicles and social robots, there is increasing realisation that machine ethics is important for widespread acceptance of autonomous machines. Our objective is to encode ethical reasoning into autonomous machines following well-defined ethical principles and behavioural norms. We provide an approach to reasoning about actions that incorporates ethical considerations. It builds on Scherl and Levesque's [29, 30] approach to knowledge in the situation calculus. We show how reasoning about knowledge in a dynamic setting can be used to guide ethical and moral choices, aligned with consequentialist and deontological approaches to ethics. We apply our approach to autonomous driving and social robot scenarios, and provide an implementation framework.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117295797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
David Solans, Francesco Fabbri, Caterina Calsamiglia, Carlos Castillo, F. Bonchi
Machine Learning (ML) techniques have been increasingly adopted by the real estate market in the last few years. Applications include, among many others, predicting the market value of a property or an area, advanced systems for managing marketing and ads campaigns, and recommendation systems based on user preferences. While these techniques can provide important benefits to the business owners and the users of the platforms, algorithmic biases can result in inequalities and loss of opportunities for groups of people who are already disadvantaged in their access to housing. In this work, we present a comprehensive and independent algorithmic evaluation of a recommender system for the real estate market, designed specifically for finding shared apartments in metropolitan areas. We were granted full access to the internals of the platform, including details on algorithms and usage data during a period of 2 years. We analyze the performance of the various algorithms which are deployed for the recommender system and asses their effect across different population groups. Our analysis reveals that introducing a recommender system algorithm facilitates finding an appropriate tenant or a desirable room to rent, but at the same time, it strengthen performance inequalities between groups, further reducing opportunities of finding a rental for certain minorities.
{"title":"Comparing Equity and Effectiveness of Different Algorithms in an Application for the Room Rental Market","authors":"David Solans, Francesco Fabbri, Caterina Calsamiglia, Carlos Castillo, F. Bonchi","doi":"10.1145/3461702.3462600","DOIUrl":"https://doi.org/10.1145/3461702.3462600","url":null,"abstract":"Machine Learning (ML) techniques have been increasingly adopted by the real estate market in the last few years. Applications include, among many others, predicting the market value of a property or an area, advanced systems for managing marketing and ads campaigns, and recommendation systems based on user preferences. While these techniques can provide important benefits to the business owners and the users of the platforms, algorithmic biases can result in inequalities and loss of opportunities for groups of people who are already disadvantaged in their access to housing. In this work, we present a comprehensive and independent algorithmic evaluation of a recommender system for the real estate market, designed specifically for finding shared apartments in metropolitan areas. We were granted full access to the internals of the platform, including details on algorithms and usage data during a period of 2 years. We analyze the performance of the various algorithms which are deployed for the recommender system and asses their effect across different population groups. Our analysis reveals that introducing a recommender system algorithm facilitates finding an appropriate tenant or a desirable room to rent, but at the same time, it strengthen performance inequalities between groups, further reducing opportunities of finding a rental for certain minorities.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123882306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificial intelligence (AI) has the potential to benefit humans and society by its employment in important sectors. However, the risks of negative consequences have underscored the importance of accountability for AI systems, their outcomes, and the users of such systems. In recent years, various accountability mechanisms have been put forward in pursuit of the responsible design, development, and use of AI. In this article, we provide an in-depth study of three such mechanisms, as we analyze Scandinavian AI developers' encounter with (1) ethical principles, (2) certification standards, and (3) explanation methods. By doing so, we contribute to closing a gap in the literature between discussions of accountability on the research and policy level, and accountability as a responsibility put on the shoulders of developers in practice. Our study illustrates important flaws in the current enactment of accountability as an ethical and social value which, if left unchecked, risks undermining the pursuit of responsible AI. By bringing attention to these flaws, the article signals where further work is needed in order to build effective accountability systems for AI.
{"title":"Situated Accountability: Ethical Principles, Certification Standards, and Explanation Methods in Applied AI","authors":"A. Henriksen, Simon Enni, A. Bechmann","doi":"10.1145/3461702.3462564","DOIUrl":"https://doi.org/10.1145/3461702.3462564","url":null,"abstract":"Artificial intelligence (AI) has the potential to benefit humans and society by its employment in important sectors. However, the risks of negative consequences have underscored the importance of accountability for AI systems, their outcomes, and the users of such systems. In recent years, various accountability mechanisms have been put forward in pursuit of the responsible design, development, and use of AI. In this article, we provide an in-depth study of three such mechanisms, as we analyze Scandinavian AI developers' encounter with (1) ethical principles, (2) certification standards, and (3) explanation methods. By doing so, we contribute to closing a gap in the literature between discussions of accountability on the research and policy level, and accountability as a responsibility put on the shoulders of developers in practice. Our study illustrates important flaws in the current enactment of accountability as an ethical and social value which, if left unchecked, risks undermining the pursuit of responsible AI. By bringing attention to these flaws, the article signals where further work is needed in order to build effective accountability systems for AI.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128646004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alex Chohlas-Wood, Joe Nudell, Zhiyuan Jerry Lin, Julian Nyarko, Sharad Goel
A prosecutor's decision to charge or dismiss a criminal case is a particularly high-stakes choice. There is concern, however, that these judgements may suffer from explicit or implicit racial bias, as with many other such actions in the criminal justice system. To reduce potential bias in charging decisions, we designed a system that algorithmically redacts race-related information from free-text case narratives. In a first-of-its-kind initiative, we deployed this system at a large American district attorney's office to help prosecutors make race-obscured charging decisions, where it was used to review many incoming felony cases. We report on both the design, efficacy, and impact of our tool for aiding equitable decision-making. We demonstrate that our redaction algorithm is able to accurately obscure race-related information, making it difficult for a human reviewer to guess the race of a suspect while preserving other information from the case narrative. In the jurisdiction we study, we found little evidence of disparate treatment in charging decisions even prior to deployment of our intervention. Thus, as expected, our tool did not substantially alter charging rates. Nevertheless, our study demonstrates the feasibility of race-obscured charging, and more generally highlights the promise of algorithms to bolster equitable decision-making in the criminal justice system.
{"title":"Blind Justice: Algorithmically Masking Race in Charging Decisions","authors":"Alex Chohlas-Wood, Joe Nudell, Zhiyuan Jerry Lin, Julian Nyarko, Sharad Goel","doi":"10.1145/3461702.3462524","DOIUrl":"https://doi.org/10.1145/3461702.3462524","url":null,"abstract":"A prosecutor's decision to charge or dismiss a criminal case is a particularly high-stakes choice. There is concern, however, that these judgements may suffer from explicit or implicit racial bias, as with many other such actions in the criminal justice system. To reduce potential bias in charging decisions, we designed a system that algorithmically redacts race-related information from free-text case narratives. In a first-of-its-kind initiative, we deployed this system at a large American district attorney's office to help prosecutors make race-obscured charging decisions, where it was used to review many incoming felony cases. We report on both the design, efficacy, and impact of our tool for aiding equitable decision-making. We demonstrate that our redaction algorithm is able to accurately obscure race-related information, making it difficult for a human reviewer to guess the race of a suspect while preserving other information from the case narrative. In the jurisdiction we study, we found little evidence of disparate treatment in charging decisions even prior to deployment of our intervention. Thus, as expected, our tool did not substantially alter charging rates. Nevertheless, our study demonstrates the feasibility of race-obscured charging, and more generally highlights the promise of algorithms to bolster equitable decision-making in the criminal justice system.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121173388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Drowsiness and fatigue are important factors in driving safety and work performance. This has motivated academic research into detecting drowsiness, and sparked interest in the deployment of related products in the insurance and work-productivity sectors. In this paper we elaborate on the potential dangers of using such algorithms. We first report on an audit of performance bias across subject gender and ethnicity, identifying which groups would be disparately harmed by the deployment of a state-of-the-art drowsiness detection algorithm. We discuss some of the sources of the bias, such as the lack of robustness of facial analysis algorithms to face occlusions, facial hair, or skin tone. We then identify potential downstream harms of this performance bias, as well as potential misuses of drowsiness detection technology---focusing on driving safety and experience, insurance cream-skimming and coverage-avoidance, worker surveillance, and job precarity.
{"title":"The Dangers of Drowsiness Detection: Differential Performance, Downstream Impact, and Misuses","authors":"Jakub Grzelak, Martim Brandao","doi":"10.1145/3461702.3462593","DOIUrl":"https://doi.org/10.1145/3461702.3462593","url":null,"abstract":"Drowsiness and fatigue are important factors in driving safety and work performance. This has motivated academic research into detecting drowsiness, and sparked interest in the deployment of related products in the insurance and work-productivity sectors. In this paper we elaborate on the potential dangers of using such algorithms. We first report on an audit of performance bias across subject gender and ethnicity, identifying which groups would be disparately harmed by the deployment of a state-of-the-art drowsiness detection algorithm. We discuss some of the sources of the bias, such as the lack of robustness of facial analysis algorithms to face occlusions, facial hair, or skin tone. We then identify potential downstream harms of this performance bias, as well as potential misuses of drowsiness detection technology---focusing on driving safety and experience, insurance cream-skimming and coverage-avoidance, worker surveillance, and job precarity.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123811967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificially intelligent systems will be used to make increasingly important decisions about us. Many of these decisions will have to be made without consensus about the relevant moral facts. I argue that what makes moral disagreement especially challenging is that there are two different ways of handling it: political solutions, which aim to find a fair compromise, and epistemic solutions, which aim at moral truth.
{"title":"Moral Disagreement and Artificial Intelligence","authors":"P. Robinson","doi":"10.1145/3461702.3462534","DOIUrl":"https://doi.org/10.1145/3461702.3462534","url":null,"abstract":"Artificially intelligent systems will be used to make increasingly important decisions about us. Many of these decisions will have to be made without consensus about the relevant moral facts. I argue that what makes moral disagreement especially challenging is that there are two different ways of handling it: political solutions, which aim to find a fair compromise, and epistemic solutions, which aim at moral truth.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"368 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116553911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Chaput, Jérémy Duval, O. Boissier, Mathieu Guillermin, S. Hassas
The recent field of Machine Ethics is experiencing rapid growth to answer the societal need for Artificial Intelligence (AI) algorithms imbued with ethical considerations, such as benevolence toward human users and actors. Several approaches already exist for this purpose, mostly either by reasoning over a set of predefined ethical principles (Top-Down), or by learning new principles (Bottom-Up). While both methods have their own advantages and drawbacks, only few works have explored hybrid approaches, such as using symbolic rules to guide the learning process for instance, combining the advantages of each. This paper draws upon existing works to propose a novel hybrid method using symbolic judging agents to evaluate the ethics of learning agents' behaviors, and accordingly improve their ability to ethically behave in dynamic multi-agent environments. Multiple benefits ensue from this separation between judging and learning agents: agents can evolve (or be updated by human designers) separately, benefiting from co-construction processes; judging agents can act as accessible proxies for non-expert human stakeholders or regulators; and finally, multiple points of view (one per judging agent) can be adopted to judge the behavior of the same agent, which produces a richer feedback. Our proposed approach is applied to an energy distribution problem, in the context of a Smart Grid simulator, with continuous and multi-dimensional states and actions. The experiments and results show the ability of learning agents to correctly adapt their behaviors to comply with the judging agents' rules, including when rules evolve over time.
{"title":"A Multi-Agent Approach to Combine Reasoning and Learning for an Ethical Behavior","authors":"R. Chaput, Jérémy Duval, O. Boissier, Mathieu Guillermin, S. Hassas","doi":"10.1145/3461702.3462515","DOIUrl":"https://doi.org/10.1145/3461702.3462515","url":null,"abstract":"The recent field of Machine Ethics is experiencing rapid growth to answer the societal need for Artificial Intelligence (AI) algorithms imbued with ethical considerations, such as benevolence toward human users and actors. Several approaches already exist for this purpose, mostly either by reasoning over a set of predefined ethical principles (Top-Down), or by learning new principles (Bottom-Up). While both methods have their own advantages and drawbacks, only few works have explored hybrid approaches, such as using symbolic rules to guide the learning process for instance, combining the advantages of each. This paper draws upon existing works to propose a novel hybrid method using symbolic judging agents to evaluate the ethics of learning agents' behaviors, and accordingly improve their ability to ethically behave in dynamic multi-agent environments. Multiple benefits ensue from this separation between judging and learning agents: agents can evolve (or be updated by human designers) separately, benefiting from co-construction processes; judging agents can act as accessible proxies for non-expert human stakeholders or regulators; and finally, multiple points of view (one per judging agent) can be adopted to judge the behavior of the same agent, which produces a richer feedback. Our proposed approach is applied to an energy distribution problem, in the context of a Smart Grid simulator, with continuous and multi-dimensional states and actions. The experiments and results show the ability of learning agents to correctly adapt their behaviors to comply with the judging agents' rules, including when rules evolve over time.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"285 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132451657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The potential for bias embedded in data to lead to the perpetuation of social injustice though Artificial Intelligence (AI) necessitates an urgent reform of data curation practices for AI systems, especially those based on machine learning. Without appropriate ethical and regulatory frameworks there is a risk that decades of advances in human rights and civil liberties may be undermined. This paper proposes an approach to data curation for AI, grounded in feminist epistemology and informed by critical theories of race and feminist principles. The objective of this approach is to support critical evaluation of the social dynamics of power embedded in data for AI systems. We propose a set of fundamental guiding principles for ethical data curation that address the social construction of knowledge, call for inclusion of subjugated and new forms of knowledge, support critical evaluation of theoretical concepts within data and recognise the reflexive nature of knowledge. In developing this ethical framework for data curation, we aim to contribute to a virtue ethics for AI and ensure protection of fundamental and human rights.
{"title":"Ethical Data Curation for AI: An Approach based on Feminist Epistemology and Critical Theories of Race","authors":"Susan Leavy, E. Siapera, B. O’Sullivan","doi":"10.1145/3461702.3462598","DOIUrl":"https://doi.org/10.1145/3461702.3462598","url":null,"abstract":"The potential for bias embedded in data to lead to the perpetuation of social injustice though Artificial Intelligence (AI) necessitates an urgent reform of data curation practices for AI systems, especially those based on machine learning. Without appropriate ethical and regulatory frameworks there is a risk that decades of advances in human rights and civil liberties may be undermined. This paper proposes an approach to data curation for AI, grounded in feminist epistemology and informed by critical theories of race and feminist principles. The objective of this approach is to support critical evaluation of the social dynamics of power embedded in data for AI systems. We propose a set of fundamental guiding principles for ethical data curation that address the social construction of knowledge, call for inclusion of subjugated and new forms of knowledge, support critical evaluation of theoretical concepts within data and recognise the reflexive nature of knowledge. In developing this ethical framework for data curation, we aim to contribute to a virtue ethics for AI and ensure protection of fundamental and human rights.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132006076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Min Kyung Lee, Ishan Nigam, Angie Zhang, J. Afriyie, Zhizhen Qin, Sicun Gao
Artificial intelligence is increasingly being used to manage the workforce. Algorithmic management promises organizational efficiency, but often undermines worker well-being. How can we computationally model worker well-being so that algorithmic management can be optimized for and assessed in terms of worker well-being? Toward this goal, we propose a participatory approach for worker well-being models. We first define worker well-being models: Work preference models---preferences about work and working conditions, and managerial fairness models---beliefs about fair resource allocation among multiple workers. We then propose elicitation methods to enable workers to build their own well-being models leveraging pairwise comparisons and ranking. As a case study, we evaluate our methods in the context of algorithmic work scheduling with 25 shift workers and 3 managers. The findings show that workers expressed idiosyncratic work preference models and more uniform managerial fairness models, and the elicitation methods helped workers discover their preferences and gave them a sense of empowerment. Our work provides a method and initial evidence for enabling participatory algorithmic management for worker well-being.
{"title":"Participatory Algorithmic Management: Elicitation Methods for Worker Well-Being Models","authors":"Min Kyung Lee, Ishan Nigam, Angie Zhang, J. Afriyie, Zhizhen Qin, Sicun Gao","doi":"10.1145/3461702.3462628","DOIUrl":"https://doi.org/10.1145/3461702.3462628","url":null,"abstract":"Artificial intelligence is increasingly being used to manage the workforce. Algorithmic management promises organizational efficiency, but often undermines worker well-being. How can we computationally model worker well-being so that algorithmic management can be optimized for and assessed in terms of worker well-being? Toward this goal, we propose a participatory approach for worker well-being models. We first define worker well-being models: Work preference models---preferences about work and working conditions, and managerial fairness models---beliefs about fair resource allocation among multiple workers. We then propose elicitation methods to enable workers to build their own well-being models leveraging pairwise comparisons and ranking. As a case study, we evaluate our methods in the context of algorithmic work scheduling with 25 shift workers and 3 managers. The findings show that workers expressed idiosyncratic work preference models and more uniform managerial fairness models, and the elicitation methods helped workers discover their preferences and gave them a sense of empowerment. Our work provides a method and initial evidence for enabling participatory algorithmic management for worker well-being.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133059800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Michiel A. Bakker, Duy Patrick Tu, K. Gummadi, A. Pentland, Kush R. Varshney, Adrian Weller
Prior work on fairness in machine learning has focused on settings where all the information needed about each individual is readily available. However, in many applications, further information may be acquired at a cost. For example, when assessing a customer's creditworthiness, a bank initially has access to a limited set of information but progressively improves the assessment by acquiring additional information before making a final decision. In such settings, we posit that a fair decision maker may want to ensure that decisions for all individuals are made with similar expected error rate, even if the features acquired for the individuals are different. We show that a set of carefully chosen confidence thresholds can not only effectively redistribute an information budget according to each individual's needs, but also serve to address individual and group fairness concerns simultaneously. Finally, using two public datasets, we confirm the effectiveness of our methods and investigate the limitations.
{"title":"Beyond Reasonable Doubt: Improving Fairness in Budget-Constrained Decision Making using Confidence Thresholds","authors":"Michiel A. Bakker, Duy Patrick Tu, K. Gummadi, A. Pentland, Kush R. Varshney, Adrian Weller","doi":"10.1145/3461702.3462575","DOIUrl":"https://doi.org/10.1145/3461702.3462575","url":null,"abstract":"Prior work on fairness in machine learning has focused on settings where all the information needed about each individual is readily available. However, in many applications, further information may be acquired at a cost. For example, when assessing a customer's creditworthiness, a bank initially has access to a limited set of information but progressively improves the assessment by acquiring additional information before making a final decision. In such settings, we posit that a fair decision maker may want to ensure that decisions for all individuals are made with similar expected error rate, even if the features acquired for the individuals are different. We show that a set of carefully chosen confidence thresholds can not only effectively redistribute an information budget according to each individual's needs, but also serve to address individual and group fairness concerns simultaneously. Finally, using two public datasets, we confirm the effectiveness of our methods and investigate the limitations.","PeriodicalId":197336,"journal":{"name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","volume":"40 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113959902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：