skip to main content

Title: Keeping Designers in the Loop: Communicating Inherent Algorithmic Trade-offs Across Multiple Objectives
Artificial intelligence algorithms have been used to enhance a wide variety of products and services, including assisting human decision making in high-stake contexts. However, these algorithms are complex and have trade-offs, notably between prediction accuracy and fairness to population subgroups. This makes it hard for designers to understand algorithms and design products or services in a way that respects users' goals, values, and needs. We proposed a method to help designers and users explore algorithms, visualize their trade-offs, and select algorithms with trade-offs consistent with their goals and needs. We evaluated our method on the problem of predicting criminal defendants' likelihood to re-offend through (i) a large-scale Amazon Mechanical Turk experiment, and (ii) in-depth interviews with domain experts. Our evaluations show that our method can help designers and users of these systems better understand and navigate algorithmic trade-offs. This paper contributes a new way of providing designers the ability to understand and control the outcomes of algorithmic systems they are creating.
Authors:
; ; ; ; ;
Award ID(s):
2001851 2000782
Publication Date:
NSF-PAR ID:
10178837
Journal Name:
Proceedings of the 2020 ACM Designing Interactive Systems Conference
Page Range or eLocation-ID:
1245 to 1257
Sponsoring Org:
National Science Foundation
More Like this
  1. With the growing industry applications of Artificial Intelligence (AI) systems, pre-trained models and APIs have emerged and greatly lowered the barrier of building AI-powered products. However, novice AI application designers often struggle to recognize the inherent algorithmic trade-offs and evaluate model fairness before making informed design decisions. In this study, we examined the Objective Revision Evaluation System (ORES), a machine learning (ML) API in Wikipedia used by the community to build anti-vandalism tools. We designed an interactive visualization system to communicate model threshold trade-offs and fairness in ORES. We evaluated our system by conducting 10 in-depth interviews with potential ORES application designers. We found that our system helped application designers who have limited ML backgrounds learn about in-context ML knowledge, recognize inherent value trade-offs, and make design decisions that aligned with their goals. By demonstrating our system in a real-world domain, this paper presents a novel visualization approach to facilitate greater accessibility and human agency in AI application design.
  2. Abstract Meeting the United Nations (UN) sustainable development goals efficiently requires designers and engineers to solve multi-objective optimization problems involving trade-offs between social, environmental, and economical impacts. This paper presents an approach for designers and engineers to quantify the social and environmental impacts of a product at a population level and then perform a trade-off analysis between those impacts. In this approach, designers and engineers define the attributes of the product as well as the materials and processes used in the product’s life cycle. Agent-based modeling (ABM) tools that have been developed to model the social impacts of products are combined with life cycle assessment (LCA) tools that have been developed to evaluate the pressures that different processes create on the environment. Designers and engineers then evaluate the trade-offs between impacts by finding non-dominated solutions that minimize environmental impacts while maximizing positive and/or minimizing negative social impacts. Product adoption models generated by ABM allow designers and engineers to approximate population level environmental impacts and avoid Simpson’s paradox, where a reversal in choices is preferred when looking at the population level impacts versus the individual product-level impacts. This analysis of impacts has the potential to help designers and engineers create moremore »impactful products that aid in reaching the UN sustainable development goals.« less
  3. Traditional recommender systems help users find the most relevant products or services to match their needs and preferences. However, they overlook the preferences of other sides of the market (aka stakeholders) involved in the system. In this paper, we propose to use contextual bandit algorithms in multi-stakeholder platforms where a multi-sided relevance function with adjusting weights is modeled to consider the preferences of all involved stakeholders. This algorithm sequentially recommends the items based on the contextual features of users along with the priority of the stakeholders and their relevance to the items.Our extensive experimental results on a dataset consisting of MovieLens (1m), IMDB (81k+), and a synthetic dataset show that our proposed approach outperforms the baseline methods and provides a good trade-off between the satisfaction of different stakeholders over time.
  4. Data-driven causality discovery is a common way to understand causal relationships among different components of a system. We study how to achieve scalable data-driven causal- ity discovery on Amazon Web Services (AWS) and Microsoft Azure cloud and propose a causality discovery as a service (CDaaS) framework. With this framework, users can easily re- run previous causality discovery experiments or run causality discovery with different setups (such as new datasets or causality discovery parameters). Our CDaaS leverages Cloud Container Registry service and Virtual Machine service to achieve scal- able causality discovery with different discovery algorithms. We further did extensive experiments and benchmarking of our CDaaS to understand the effects of seven factors (big data engine parameter setting, virtual machine instance number, type, subtype, size, cloud service, cloud provider) and how to best provision cloud resources for our causality discovery service based on certain goals including execution time, budgetary cost and cost-performance ratio. We report our findings from the benchmarking, which can help obtain optimal configurations based on each application’s characteristics. The findings show proper configurations could lead to both faster execution time and less budgetary cost.
  5. Children use popular web search tools, which are generally designed for adult users. Because children have different developmental needs than adults, these tools may not always adequately support their search for information. Moreover, even though search tools offer support to help in query formulation, these too are aimed at adults and may hinder children rather than help them. This calls for the examination of existing technologies in this area, to better understand what remains to be done when it comes to facilitating query-formulation tasks for young users. In this paper, we investigate interaction elements of query formulation--including query suggestion algorithms--for children. The primary goals of our research efforts are to: (i) examine existing plug-ins and interfaces that explicitly aid children's query formulation; (ii) investigate children's interactions with suggestions offered by a general-purpose query suggestion strategy vs. a counterpart designed with children in mind; and (iii) identify, via participatory design sessions, their preferences when it comes to tools / strategies that can help children find information and guide them through the query formulation process. Our analysis shows that existing tools do not meet children's needs and expectations; the outcomes of our work can guide researchers and developers as they implement querymore »formulation strategies for children.« less