Local interpretation of supervised learning models based on high dimensional model representation

Machine learning models have been widely used to obtain prediction in various domains; however, most of such models are black boxes owing to the high complexity. The lack of transparency of machine learning models hampers their applications because the practi-tioners do not understand the internal mechanism of these models. This study proposes a model-agnostic method, based on the high dimensional model representation (HDMR), to interpret supervised learning models by determining the local feature contribution. Compared to the existing methods, which only assign a single value to the feature contri-bution and do not consider the feature dependence, the HDMR-based feature contribution can be decomposed into individual and combined contribution, and it can take feature dependence into account. Certain agnostic and specific methods to measure the HDMR-based feature contributions are developed and categorized as pertaining to either feature independence or dependence. Experiments are performed to demonstrate the effects of the HDMR-based feature contributions, and compare the performance of several estima-tion methods. ? 2021 Elsevier Inc. All rights reserved.

Automated summary

A model-agnostic method based on high dimensional model representation (HDMR) is proposed to interpret supervised learning models by determining local feature contribution. Compared to existing methods, this approach can better consider feature dependence.