HCOct 7, 2019

Keeping Designers in the Loop: Communicating Inherent Algorithmic Trade-offs Across Multiple Objectives

arXiv:1910.03061v39 citations
Originality Incremental advance
AI Analysis

This addresses the challenge for designers in creating AI systems that respect user values, though it is incremental in providing tools for existing trade-off exploration.

The paper tackled the problem of helping designers understand and navigate trade-offs in AI algorithms, such as between accuracy and fairness, by proposing a method for visualizing and selecting algorithms aligned with user goals, evaluated through experiments and expert interviews showing improved understanding.

Artificial intelligence algorithms have been used to enhance a wide variety of products and services, including assisting human decision making in high-stakes 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes