Handling missing values in local post-hoc explainability

Missing data are quite common in real scenarios when using Artificial Intelligence (AI) systems for decision-making with tabular data and effectively handling them poses a significant challenge for such systems. While some machine learning models used by AI systems can tackle this problem, the existing literature lacks post-hoc explainability approaches able to deal with predictors that encounter missing data. In this paper, we extend a widely used local model-agnostic post-hoc explanation approach that enables explainability in the presence of missing values by incorporating state-of-the-art imputation methods within the explanation process. Since our proposal returns explanations in the form of feature importance, the user will be aware also of the importance of a missing value in a given record for a particular prediction. Extensive experiments show the effectiveness of the proposed method with respect to some baseline solutions relying on traditional data imputation.