Timezone: »

 
Flexible Interpretability through Optimizable Counterfactual Explanations for Tree Ensembles
Ana Lucic · Harrie Oosterhuis · Hinda Haned · Maarten de Rijke

@
in Workshop on Socially Responsible Machine Learning »

Model interpretability has become an important problem in \ac{ML} due to the increased effect algorithmic decisions have on humans. Providing users with counterfactual explanations (CF) can help them understand not only why ML models make certain decisions, but also how these decisions can be changed. We extend previous work that could only be applied to differentiable models by introducing probabilistic model approximations in the optimization framework. We find that our CF examples are significantly closer to the original instances compared to other methods specifically designed for tree ensembles.

Author Information

Ana Lucic (Partnership on AI, University of Amsterdam)

Research fellow at the Partnership on AI and PhD student at the University of Amsterdam, working primarily on explainable ML.

Harrie Oosterhuis (Radboud University)
Hinda Haned (University of Amsterdam)
Maarten de Rijke (University of Amsterdam)

More from the Same Authors