Artificial Intelligence (AI) is often an integral part of modern decision support systems (DSSs). The best-performing predictive models used in AI-based DSSs lack transparency. Explainable Artificial Intelligence (XAI) aims to create AI systems that can explain their rationale to human users. Local explanations in XAI can provide information about the causes of individual predictions in terms of feature importance. However, a critical drawback of existing local explanation methods is their inability to quantify the uncertainty associated with a feature's importance. This paper introduces an extension of a feature importance explanation method, Calibrated Explanations (CE), previously only supporting classification, with support for standard regression and probabilistic regression, i.e., the probability that the target is above an arbitrary threshold. The extension for regression keeps all the benefits of CE, such as calibration of the prediction from the underlying model with confidence intervals, uncertainty quantification of feature importance, and allows both factual and counterfactual explanations. CE for standard regression provides fast, reliable, stable, and robust explanations. CE for probabilistic regression provides an entirely new way of creating probabilistic explanations from any ordinary regression model and with a dynamic selection of thresholds. The performance of CE for probabilistic regression regarding stability and speed is comparable to LIME. The method is model agnostic with easily understood conditional rules. An implementation in Python is freely available on GitHub and for installation using pip making the results in this paper easily replicable.

翻译：摘要：人工智能（AI）常是现代决策支持系统（DSS）的核心组成部分，而基于AI的DSS中性能最优的预测模型往往缺乏可解释性。可解释人工智能（XAI）旨在构建能够向人类用户解释其推理逻辑的AI系统。XAI中的局部解释方法可通过特征重要性信息揭示单个预测结果的成因。然而，现有局部解释方法的关键缺陷在于无法量化特征重要性的不确定性。本文提出一种扩展的特征重要性解释方法——校准解释（Calibrated Explanations, CE），该方法此前仅支持分类任务，现拓展至标准回归与概率回归（即目标值超过任意阈值的概率）。回归扩展版本保留了CE的全部优势，例如：通过置信区间校准底层模型的预测、量化特征重要性的不确定性，并同时支持事实解释与反事实解释。面向标准回归的CE能够提供快速、可靠、稳定且鲁棒的解释；面向概率回归的CE则开创性地实现了从任意普通回归模型中生成概率解释的方法，且支持阈值的动态选择。在稳定性与运行速度方面，面向概率回归的CE性能与LIME相当。该方法具备模型无关特性，并采用易于理解的规则进行表达。文中实现基于Python的开源代码已发布于GitHub，并支持通过pip安装，确保研究结果可轻松复现。