There are two things to be considered when we evaluate predictive models. One is prediction accuracy,and the other is interpretability. Over the recent decades, many prediction models of high performance, such as ensemble-based models and deep neural networks, have been developed. However, these models are often too complex, making it difficult to intuitively interpret their predictions. This complexity in interpretation limits their use in many real-world fields that require accountability, such as medicine, finance, and college admissions. In this study, we develop a novel method called Meta-ANOVA to provide an interpretable model for any given prediction model. The basic idea of Meta-ANOVA is to transform a given black-box prediction model to the functional ANOVA model. A novel technical contribution of Meta-ANOVA is a procedure of screening out unnecessary interaction before transforming a given black-box model to the functional ANOVA model. This screening procedure allows the inclusion of higher order interactions in the transformed functional ANOVA model without computational difficulties. We prove that the screening procedure is asymptotically consistent. Through various experiments with synthetic and real-world datasets, we empirically demonstrate the superiority of Meta-ANOVA

翻译：在评估预测模型时，需要考虑两个因素：一是预测准确性，二是可解释性。近几十年来，人们开发了许多高性能预测模型，例如基于集成的模型和深度神经网络。然而，这些模型往往过于复杂，难以直观解释其预测结果。这种解释上的复杂性限制了它们在许多需要问责的现实领域（如医学、金融和大学招生）中的应用。在本研究中，我们开发了一种名为Meta-ANOVA的新方法，旨在为任意给定的预测模型提供可解释的模型表示。Meta-ANOVA的基本思想是将给定的黑盒预测模型转换为函数方差分析（functional ANOVA）模型。该方法的一项创新技术贡献在于：在将给定黑盒模型转换为函数方差分析模型之前，通过筛选程序剔除不必要的交互作用。该筛选机制使得转换后的函数方差分析模型能够包含高阶交互项而不会产生计算困难。我们证明了该筛选过程具有渐近一致性。通过对合成数据集和真实数据集的多种实验，我们实证验证了Meta-ANOVA的优越性。