LORE

LORE ia a black box agnostic method able to provide interpretable and
faithful explanations. LORE first learns a local interpretable predictor on
a synthetic neighborhood generated by a genetic algorithm. Then it derives
from the logic of the local interpretable predictor a meaningful
explanation consisting of: a decision rule, which explains the reasons of
the decision; and a set of counterfactual rules, proactively suggesting the
changes in the instance features that lead to a different outcome.

Details of the methos are presented in [1]
The software implemented in Python is available at [2].
Documentation and source code repository at [3]



[1] https://arxiv.org/pdf/1805.10820.pdf
[2] https://ckan-sobigdata.d4science.org/dataset/lorem
[3] https://github.com/riccotti/LORE