论文标题
准确性对模型解释的影响
Impact of Accuracy on Model Interpretations
论文作者
论文摘要
模型解释通常在实践中用于从机器学习模型中提取现实世界的见解。这些解释具有广泛的应用。它们可以作为业务建议提出或用于评估模型偏见。对于数据科学家来说，选择值得信赖的解释来推动现实世界的影响至关重要。这样做需要了解模型的准确性如何影响标准解释工具的质量。在本文中，我们将探讨模型的预测精度如何影响解释质量。我们建议两个指标来量化解释的质量并设计实验，以测试这些指标如何随模型准确性而变化。我们发现，对于可以通过多种方法准确建模的数据集，更简单的方法会产生更高质量的解释。我们还确定哪种解释方法最适合较低的模型准确性。
Model interpretations are often used in practice to extract real world insights from machine learning models. These interpretations have a wide range of applications; they can be presented as business recommendations or used to evaluate model bias. It is vital for a data scientist to choose trustworthy interpretations to drive real world impact. Doing so requires an understanding of how the accuracy of a model impacts the quality of standard interpretation tools. In this paper, we will explore how a model's predictive accuracy affects interpretation quality. We propose two metrics to quantify the quality of an interpretation and design an experiment to test how these metrics vary with model accuracy. We find that for datasets that can be modeled accurately by a variety of methods, simpler methods yield higher quality interpretations. We also identify which interpretation method works the best for lower levels of model accuracy.
