Better Together? How Externalities of Size Complicate Notions of Solidarity and Actuarial Fairness

• URL: http://arxiv.org/abs/2103.00347v2
• Date: Wed, 1 Dec 2021 17:52:47 GMT
• Title: Better Together? How Externalities of Size Complicate Notions of Solidarity and Actuarial Fairness
• Authors: Kate Donahue and Solon Barocas
• Abstract summary: Two notions of fairness might be to a) charge each individual the same price or b) charge each individual according to the cost that they bring to the pool. We show that it is possible for both groups (high and low risk) to strictly benefit by joining an insurance pool where costs are evenly split, as opposed to being in separate risk pools. We build on this by producing a pricing scheme that maximally subsidizes the high risk group, while maintaining an incentive for lower risk people to stay in the insurance pool.
• Score: 4.94950858749529
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Consider a cost-sharing game with players of different contribution to the total cost: an example might be an insurance company calculating premiums for a population of mixed-risk individuals. Two natural and competing notions of fairness might be to a) charge each individual the same price or b) charge each individual according to the cost that they bring to the pool. In the insurance literature, these general approaches are referred to as "solidarity" and "actuarial fairness" and are commonly viewed as opposites. However, in insurance (and many other natural settings), the cost-sharing game also exhibits "externalities of size": all else being equal, larger groups have lower average cost. In the insurance case, we analyze a model with externalities of size due to a reduction in the variability of losses. We explore how this complicates traditional understandings of fairness, drawing on literature in cooperative game theory. First, we explore solidarity: we show that it is possible for both groups (high and low risk) to strictly benefit by joining an insurance pool where costs are evenly split, as opposed to being in separate risk pools. We build on this by producing a pricing scheme that maximally subsidizes the high risk group, while maintaining an incentive for lower risk people to stay in the insurance pool. Next, we demonstrate that with this new model, the price charged to each individual has to depend on the risk of other participants, making naive actuarial fairness inefficient. Furthermore, we prove that stable pricing schemes must be ones where players have the anti-social incentive of desiring riskier partners, contradicting motivations for using actuarial fairness. Finally, we describe how these results relate to debates about fairness in machine learning and potential avenues for future research.

Related papers

• Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality [62.18973784316808]
  In economic theory, the concept of externality refers to any indirect effect resulting from an interaction between players that affects the social welfare. Our work removes the classical assumption that bargainers possess perfect knowledge of the underlying game. We then design a policy for the players which allows them to learn a bargaining strategy which maximizes the total welfare.
  arXiv  Detail & Related papers  (2024-06-28T11:00:53Z)
• Fairness Incentives in Response to Unfair Dynamic Pricing [7.991187769447732]
  We design a basic simulated economy, wherein we generate corporate taxation schedules geared to incentivizing firms towards adopting fair pricing behaviours. To cover a range of possible policy scenarios, we formulate our social planner's learning problem as a multi-armed bandit, a contextual bandit and as a full reinforcement learning (RL) problem. We find that social welfare improves on that of the fairness-agnostic baseline, and approaches that of the analytically optimal fairness-aware baseline for the multi-armed and contextual bandit settings.
  arXiv  Detail & Related papers  (2024-04-22T23:12:58Z)
• Auditing Fairness under Unobserved Confounding [56.61738581796362]
  We show that we can still give meaningful bounds on treatment rates to high-risk individuals, even when entirely eliminating or relaxing the assumption that all relevant risk factors are observed. This result is of immediate practical interest: we can audit unfair outcomes of existing decision-making systems in a principled manner.
  arXiv  Detail & Related papers  (2024-03-18T21:09:06Z)
• On the Societal Impact of Open Foundation Models [93.67389739906561]
  We focus on open foundation models, defined here as those with broadly available model weights. We identify five distinctive properties of open foundation models that lead to both their benefits and risks.
  arXiv  Detail & Related papers  (2024-02-27T16:49:53Z)
• Measuring and Mitigating Biases in Motor Insurance Pricing [1.2289361708127877]
  The non-life insurance sector operates within a highly competitive and tightly regulated framework. Age-based premium fairness is also mandated in certain insurance domains. In certain insurance domains, variables such as the presence of serious illnesses or disabilities are emerging as new dimensions for evaluating fairness.
  arXiv  Detail & Related papers  (2023-11-20T16:34:48Z)
• A Discussion of Discrimination and Fairness in Insurance Pricing [0.0]
  Group fairness concepts are proposed to'smooth out' the impact of protected characteristics in the calculation of insurance prices. We present a statistical model that is free of proxy discrimination, thus, unproblematic from an insurance pricing point of view. We find that the canonical price in this statistical model does not satisfy any of the three most popular group fairness axioms.
  arXiv  Detail & Related papers  (2022-09-02T07:31:37Z)
• Joint Multisided Exposure Fairness for Recommendation [76.75990595228666]
  This paper formalizes a family of exposure fairness metrics that model the problem jointly from the perspective of both the consumers and producers. Specifically, we consider group attributes for both types of stakeholders to identify and mitigate fairness concerns that go beyond individual users and items towards more systemic biases in recommendation.
  arXiv  Detail & Related papers  (2022-04-29T19:13:23Z)
• A Fair Pricing Model via Adversarial Learning [3.983383967538961]
  At the core of insurance business lies classification between risky and non-risky insureds. The distinction between a fair actuarial classification and "discrimination" is subtle. We show that debiasing the predictor alone may be insufficient to maintain adequate accuracy.
  arXiv  Detail & Related papers  (2022-02-24T10:42:20Z)
• Identifying Undercompensated Groups Defined By Multiple Attributes in Risk Adjustment [0.09137554315375918]
  We evaluate the risk adjustment formulas used in the U.S. health insurance Marketplaces and Medicare. We find that groups with multiple chronic conditions are undercompensated in the Marketplaces risk adjustment formula. No complex groups were found to be consistently under- or overcompensated in the Medicare risk adjustment formula.
  arXiv  Detail & Related papers  (2021-05-18T13:09:13Z)
• 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)
• Competing Bandits: The Perils of Exploration Under Competition [119.39607854637798]
  We study the interplay between exploration and competition on online platforms. We find that stark competition induces firms to commit to a "greedy" bandit algorithm that leads to low welfare. We investigate two channels for weakening the competition: relaxing the rationality of users and giving one firm a first-mover advantage.
  arXiv  Detail & Related papers  (2020-07-20T14:19:08Z)

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.