skip to main content

Title: Soliciting Stakeholders’ Fairness Notions in Child Maltreatment Predictive Systems
Recent work in fair machine learning has proposed dozens of technical definitions of algorithmic fairness and methods for enforcing these definitions. However, we still lack an understanding of how to develop machine learning systems with fairness criteria that reflect relevant stakeholders’ nuanced viewpoints in real-world contexts. To address this gap, we propose a framework for eliciting stakeholders’ subjective fairness notions. Combining a user interface that allows stakeholders to examine the data and the algorithm’s predictions with an interview protocol to probe stakeholders’ thoughts while they are interacting with the interface, we can identify stakeholders’ fairness beliefs and principles. We conduct a user study to evaluate our framework in the setting of a child maltreatment predictive system. Our evaluations show that the framework allows stakeholders to comprehensively convey their fairness viewpoints. We also discuss how our results can inform the design of predictive systems.  more » « less
Award ID(s):
2001851 2000782
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
CHI '21: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems
Page Range / eLocation ID:
1 to 17
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Recommender systems have a variety of stakeholders. Applying concepts of fairness in such systems requires attention to stakeholders’ complex and often-conflicting needs. Since fairness is socially constructed, there are numerous definitions, both in the social science and machine learning literatures. Still, it is rare for machine learning researchers to develop their metrics in close consideration of their social context. More often, standard definitions are adopted and assumed to be applicable across contexts and stakeholders. Our research starts with a recommendation context and then seeks to understand the breadth of the fairness considerations of associated stakeholders. In this paper, we report on the results of a semi-structured interview study with 23 employees who work for the Kiva microlending platform. We characterize the many different ways in which they enact and strive toward fairness for microlending recommendations in their own work, uncover the ways in which these different enactments of fairness are in tension with each other, and identify how stakeholders are differentially prioritized. Finally, we reflect on the implications of this study for future research and for the design of multistakeholder recommender systems. 
    more » « less
  2. Group fairness definitions such as Demographic Parity and Equal Opportunity make assumptions about the underlying decision-problem that restrict them to classification problems. Prior work has translated these definitions to other machine learning environments, such as unsupervised learning and reinforcement learning, by implementing their closest mathematical equivalent. As a result, there are numerous bespoke interpretations of these definitions. This work aims to unify the shared aspects of each of these bespoke definitions, and to this end we provide a group fairness framework that generalizes beyond just classification problems. We leverage two fairness principles that enable this generalization. First, our framework measures outcomes in terms of utilities, rather than predictions, and does so for both the decision-maker and the individual. Second, our framework can consider counterfactual outcomes, rather than just observed outcomes, thus preventing loopholes where fairness criteria are satisfied through self-fulfilling prophecies. We provide concrete examples of how our utility fairness framework avoids these assumptions and thus naturally integrates with classification, clustering, and reinforcement learning fairness problems. We also show that many of the bespoke interpretations of Demographic Parity and Equal Opportunity fit nicely as special cases of our framework.

    more » « less
  3. We propose definitions of fairness in machine learning and artificial intelligence systems that are informed by the framework of intersectionality, a critical lens from the legal, social science, and humanities literature which analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including gender, race, sexual orientation, class, and disability. We show that our criteria behave sensibly for any subset of the set of protected attributes, and we prove economic, privacy, and generalization guarantees. Our theoretical results show that our criteria meaningfully operationalize AI fairness in terms of real-world harms, making the measurements interpretable in a manner analogous to differential privacy. We provide a simple learning algorithm using deterministic gradient methods, which respects our intersectional fairness criteria. The measurement of fairness becomes statistically challenging in the minibatch setting due to data sparsity, which increases rapidly in the number of protected attributes and in the values per protected attribute. To address this, we further develop a practical learning algorithm using stochastic gradient methods which incorporates stochastic estimation of the intersectional fairness criteria on minibatches to scale up to big data. Case studies on census data, the COMPAS criminal recidivism dataset, the HHP hospitalization data, and a loan application dataset from HMDA demonstrate the utility of our methods. 
    more » « less
  4. null (Ed.)
    Recently, there have been increasing calls for computer science curricula to complement existing technical training with topics related to Fairness, Accountability, Transparency and Ethics (FATE). In this paper, we present Value Cards, an educational toolkit to inform students and practitioners the social impacts of different machine learning models via deliberation. This paper presents an early use of our approach in a college-level computer science course. Through an in-class activity, we report empirical data for the initial effectiveness of our approach. Our results suggest that the use of the Value Cards toolkit can improve students' understanding of both the technical definitions and trade-offs of performance metrics and apply them in real-world contexts, help them recognize the significance of considering diverse social values in the development and deployment of algorithmic systems, and enable them to communicate, negotiate and synthesize the perspectives of diverse stakeholders. Our study also demonstrates a number of caveats we need to consider when using the different variants of the Value Cards toolkit. Finally, we discuss the challenges as well as future applications of our approach. 
    more » « less
  5. Sudeepa Roy and Jun Yang (Ed.)
    Data we encounter in the real-world such as printed menus, business documents, and nutrition labels, are often ad-hoc. Valuable insights can be gathered from this data when combined with additional information. Recent advances in computer vision and augmented reality have made it possible to understand and enrich such data. Joining real-world data with remote data stores and surfacing those enhanced results in place, within an augmented reality interface can lead to better and more informed decision-making capabilities. However, building end-user applications that perform these joins with minimal human effort is not straightforward. It requires a diverse set of expertise, including machine learning, database systems, computer vision, and data visualization. To address this complexity, we present Quill – a framework to develop end-to-end applications that model augmented reality applications as a join between real- world data and remote data stores. Using an intuitive domain-specific language, Quill accelerates the development of end-user applications that join real-world data with remote data stores. Through experiments on applications from multiple different domains, we show that Quill not only expedites the process of development, but also allows developers to build applications that are more performant than those built using standard developer tools, thanks to the ability to optimize declarative specifications. We also perform a user-focused study to investigate how easy (or difficult) it is to use Quill for developing augmented reality applications than other existing tools. Our results show that Quill allows developers to build and deploy applications with a lower technical background than building the same application using existing developer tools. 
    more » « less