Reason to explain : interactive contrastive explanations (REASONX)

Many high-performing machine learning models are not in- terpretable. As they are increasingly used in decision scenarios that can critically affect individuals, it is necessary to develop tools to better un- derstand their outputs. Popular explanation methods include contrastive explanations. However, they suffer several shortcomings, among others an insufficient incorporation of background knowledge, and a lack of interactivity. While (dialogue-like) interactivity is important to better communicate an explanation, background knowledge has the potential to significantly improve their quality, e.g., by adapting the explanation to the needs of the end-user. To close this gap, we present reasonx, an explanation tool based on Con- straint Logic Programming (CLP). reasonx provides interactive con- trastive explanations that can be augmented by background knowledge, and allows to operate under a setting of under-specified information, leading to increased flexibility in the provided explanations. reasonx computes factual and constrative decision rules, as well as closest con- strative examples. It provides explanations for decision trees, which can be the ML models under analysis, or global/local surrogate models of any ML model. While the core part of reasonx is built on CLP, we also provide a pro- gram layer that allows to compute the explanations via Python, making the tool accessible to a wider audience. We illustrate the capability of reasonx on a synthetic data set, and on a a well-developed example in the credit domain. In both cases, we can show how reasonx can be flexibly used and tailored to the needs of the user