The whole idea behind interpretable and explainable ML is to avoid the black box effect.
While there is some room for error while integrating models into production environments, there is also a very good probability that these issues will eventually lead to disaster. And that’s exactly why we have created this pre-model deployment checklist.
Better features, better data
Demystifying the old battle between transparent, explainable models and more accurate, complex models.
(or – “how I f***ed up my text classifier while thinking it’s performing well")