Remove 2016 Remove Knowledge Discovery Remove Risk Remove Visualization
article thumbnail

Explaining black-box models using attribute importance, PDPs, and LIME

Domino Data Lab

2016) for an example of this technique (LIME). Skater provides a wide range of algorithms that can be used for visual interpretation (e.g. This dataset classifies customers based on a set of attributes into two credit risk groups – good or bad. See Ribeiro et al. layer-wise relevance propagation), model distillation (e.g.

Modeling 139