Causal Fairness for Outcome Control

• URL: http://arxiv.org/abs/2306.05066v1
• Date: Thu, 8 Jun 2023 09:31:18 GMT
• Title: Causal Fairness for Outcome Control
• Authors: Drago Plecko, Elias Bareinboim
• Abstract summary: We study a specific decision-making task called outcome control in which an automated system aims to optimize an outcome variable $Y$ while being fair and equitable. In this paper, we first analyze through causal lenses the notion of benefit, which captures how much a specific individual would benefit from a positive decision. We then note that the benefit itself may be influenced by the protected attribute, and propose causal tools which can be used to analyze this.
• Score: 68.12191782657437
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As society transitions towards an AI-based decision-making infrastructure, an ever-increasing number of decisions once under control of humans are now delegated to automated systems. Even though such developments make various parts of society more efficient, a large body of evidence suggests that a great deal of care needs to be taken to make such automated decision-making systems fair and equitable, namely, taking into account sensitive attributes such as gender, race, and religion. In this paper, we study a specific decision-making task called outcome control in which an automated system aims to optimize an outcome variable $Y$ while being fair and equitable. The interest in such a setting ranges from interventions related to criminal justice and welfare, all the way to clinical decision-making and public health. In this paper, we first analyze through causal lenses the notion of benefit, which captures how much a specific individual would benefit from a positive decision, counterfactually speaking, when contrasted with an alternative, negative one. We introduce the notion of benefit fairness, which can be seen as the minimal fairness requirement in decision-making, and develop an algorithm for satisfying it. We then note that the benefit itself may be influenced by the protected attribute, and propose causal tools which can be used to analyze this. Finally, if some of the variations of the protected attribute in the benefit are considered as discriminatory, the notion of benefit fairness may need to be strengthened, which leads us to articulating a notion of causal benefit fairness. Using this notion, we develop a new optimization procedure capable of maximizing $Y$ while ascertaining causal fairness in the decision process.

Related papers

• Fairness-Accuracy Trade-Offs: A Causal Perspective [58.06306331390586]
  We analyze the tension between fairness and accuracy from a causal lens for the first time. We show that enforcing a causal constraint often reduces the disparity between demographic groups. We introduce a new neural approach for causally-constrained fair learning.
  arXiv  Detail & Related papers  (2024-05-24T11:19:52Z)
• Assessing Group Fairness with Social Welfare Optimization [0.9217021281095907]
  This paper explores whether a broader conception of social justice, based on optimizing a social welfare function, can be useful for assessing various definitions of parity. We show that it can justify demographic parity or equalized odds under certain conditions, but frequently requires a departure from these types of parity. In addition, we find that predictive rate parity is of limited usefulness.
  arXiv  Detail & Related papers  (2024-05-19T01:41:04Z)
• Social Diversity Reduces the Complexity and Cost of Fostering Fairness [63.70639083665108]
  We investigate the effects of interference mechanisms which assume incomplete information and flexible standards of fairness. We quantify the role of diversity and show how it reduces the need for information gathering. Our results indicate that diversity changes and opens up novel mechanisms available to institutions wishing to promote fairness.
  arXiv  Detail & Related papers  (2022-11-18T21:58:35Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• A Justice-Based Framework for the Analysis of Algorithmic Fairness-Utility Trade-Offs [0.0]
  In prediction-based decision-making systems, different perspectives can be at odds. The short-term business goals of the decision makers are often in conflict with the decision subjects' wish to be treated fairly. We propose a framework to make these value-laden choices clearly visible.
  arXiv  Detail & Related papers  (2022-06-06T20:31:55Z)
• Towards a Fairness-Aware Scoring System for Algorithmic Decision-Making [35.21763166288736]
  We propose a general framework to create data-driven fairness-aware scoring systems. We show that the proposed framework provides practitioners or policymakers great flexibility to select their desired fairness requirements.
  arXiv  Detail & Related papers  (2021-09-21T09:46:35Z)
• Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems [0.0]
  We argue that for an effective explanation, perceptions of fairness should increase if and only if the underlying ADS is fair. In this in-progress work, we introduce the desideratum of appropriate fairness perceptions, propose a novel study design for evaluating it, and outline next steps towards a comprehensive experiment.
  arXiv  Detail & Related papers  (2021-08-14T09:39:59Z)
• Fairness, Welfare, and Equity in Personalized Pricing [88.9134799076718]
  We study the interplay of fairness, welfare, and equity considerations in personalized pricing based on customer features. We show the potential benefits of personalized pricing in two settings: pricing subsidies for an elective vaccine, and the effects of personalized interest rates on downstream outcomes in microcredit.
  arXiv  Detail & Related papers  (2020-12-21T01:01:56Z)
• Fair Influence Maximization: A Welfare Optimization Approach [34.39574750992602]
  We provide a principled characterization of the properties that a fair influence algorithm should satisfy. Under this framework, the trade-off between fairness and efficiency can be controlled by a single design aversion parameter. Our framework encompasses as special cases leximin and proportional fairness.
  arXiv  Detail & Related papers  (2020-06-14T14:08:10Z)
• On Consequentialism and Fairness [64.35872952140677]
  We provide a consequentialist critique of common definitions of fairness within machine learning. We conclude with a broader discussion of the issues of learning and randomization.
  arXiv  Detail & Related papers  (2020-01-02T05:39:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.