FairSight: Visual Analytics for Fairness in Decision Making

Abstract

Fig. 1. We propose a design framework to protect individuals and groups from discrimination in algorithm-assisted decision making. A visual analytic system, FairSight, is implemented based on our proposed framework, to help data scientists and practitioners make fair decisions. The decision is made through ranking individuals who are either members of a protected group (orange bars) or a non-protected group (green bars). (a) The system provides a pipeline to help users understand the possible bias in a machine learning task as a mapping from the input space to the output space. (b) Different notions of fairnessindividual fairness and group fairnessare measured and summarized numerically and visually. For example, the individual fairness is quantified by how pairwise distances between individuals are preserved through the mapping. The group fairness is quantified by the extent to which it leads to fair outcome distribution across groups, with (i) a 2D plot, (ii) a color-coded matrix , and (iii) a ranked-list plot capturing the pattern of potential biases.The system provides diagnostic modules to help (iv) identify and (v) mitigate biases through (c) investigating features before running a model, and (d) leveraging fairness-aware algorithms during and after the training step.Abstract-Data-driven decision making related to individuals has become increasingly pervasive, but the issue concerning the potential discrimination has been raised by recent studies. In response, researchers have made efforts to propose and implement fairness measures and algorithms, but those efforts have not been translated to the real-world practice of data-driven decision making. As such, there is still an urgent need to create a viable tool to facilitate fair decision making. We propose FairSight, a visual analytic system to address this need; it is designed to achieve different notions of fairness in ranking decisions through identifying the required actions -understanding, measuring, diagnosing and mitigating biases -that together lead to fairer decision making. Through a case study and user study, we demonstrate that the proposed visual analytic and diagnostic modules in the system are effective in understanding the fairness-aware decision pipeline and obtaining more fair outcomes.

Boxer: Interactive Comparison of Classifier Results

“…Cabrera et al [CEH*19] present a method for analyzing fairness by generating subsets of the data with different prediction performance. In contrast, Ahn and Lin [AL20] focus on identifying instance‐level bias. In contrast, our approach supports a broad range of tasks with flexible mechanisms to analyze different aspects of data and classifier performance.…”

A survey of visual analytics techniques for machine learning

“…Using different textures to encode true/false positives/negatives, this tool allows fast and accurate estimation of performance metrics at multiple levels of detail. Recently, the issue of model fairness has drawn growing attention [80,83,97]. For example, Ahn et al [80] proposed a framework named FairSight and implemented a visual analytics system to support the analysis of fairness in ranking problems.…”

“…Recently, the issue of model fairness has drawn growing attention [80,83,97]. For example, Ahn et al [80] proposed a framework named FairSight and implemented a visual analytics system to support the analysis of fairness in ranking problems. They divided the machine learning pipeline into three phases (data, model, and outcome) and then measured the bias both at individual and group levels using different measures.…”

The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations

“…The paper presents an interactive visualization technique to assist novice users of ML to understand, examine, and verify the performance of predictive models. FairSight [AL20] is another tool designed to accomplish different concepts of fairness in ranking decisions. To achieve that, FairSight distinguishes the required actions (understanding, computing, and others) that can possibly lead to fairer decision making.…”

“…With the comparison of various models and learning methods, it allows users to become knowledgeable about their usability. Fair‐Sight [AL20] which was discussed earlier along with the What‐If Tool [WPB*20] are both two recent examples of how fairness is a trending unexplored subject in the community. The What‐If Tool (which was not discussed yet) enables domain experts to assess the performance of models in hypothetical scenarios, analyze the significance of several data features, and visualize model functionality across many ML models and batches of input data.…”