Systems that offer continuous model monitoring have emerged in response to (1) well-documented failures of deployed Machine Learning (ML) and Artificial Intelligence (AI) models and (2) new regulatory requirements impacting these models. Existing monitoring systems continuously track the performance of deployed ML models and compute feature importance (a.k.a. explanations) for each prediction to help developers identify the root causes of emergent model performance problems. We present Quantile Demographic Drift (QDD), a novel model bias quantification metric that uses quantile binning to measure differences in the overall prediction distributions over subgroups. QDD is ideal for continuous monitoring scenarios, does not suffer from the statistical limitations of conventional threshold-based bias metrics, and does not require outcome labels (which may not be available at runtime). We incorporate QDD into a continuous model monitoring system, called FairCanary, that reuses existing explanations computed for each individual prediction to quickly compute explanations for the QDD bias metrics. This optimization makes FairCanary an order of magnitude faster than previous work that has tried to generate feature-level bias explanations.

翻译：为应对（1）已部署机器学习（ML）与人工智能（AI）模型被充分记录的失效案例，以及（2）影响这些模型的新监管要求，能够提供连续模型监控的系统应运而生。现有监控系统持续追踪已部署ML模型的性能，并针对每次预测计算特征重要性（即解释），以帮助开发者识别模型性能问题的根本原因。本文提出分位数人口漂移（QDD）这一新型模型偏差量化指标，该方法利用分位数分箱来测量子群体间整体预测分布的差异。QDD适用于连续监控场景，不存在传统基于阈值的偏差指标的统计局限性，且无需依赖运行时可能缺失的结果标签。我们将QDD集成到名为FairCanary的连续模型监控系统中，该系统复用为每次预测预先计算的现有解释，快速生成QDD偏差指标的解释。该优化使FairCanary的速度比先前试图生成特征级偏差解释的研究提升一个数量级。