Questions related to the Locally Interpretable Model-Agnostic Explanations (LIME) method of explaining black-box machine learning models.

Lime stands for Locally Interpretable Model-Agnostic Explanations. It is a method developed by Ribeiro. He has a short blog post explaining the idea here, and a paper introducing the technique here (pdf). Very briefly, given a prediction at a certain location in the covariate space, LIME fits a linear model to simulated data and the model's predictions for them in the neighborhood of the original prediction. This allows the analyst to see what features are influential there.