Machine Learning can often be a black box. To gain actionable insights, its helpful to know how a variable influences a model. Here we outline 5 ways to assess feature importance to affecting the probability of an outcome. (more…)

This blog post is my attempt to give an overview of the sub-field of machine learning interpretability. I do not intend for this post to be necessarily comprehensive, but my goal is to review conceptual frameworks, existing research, and future directions... (more…)

Machine learning (ML) models are susceptible to unintended biases as much as we do. The good news is we can design them not to be. (more…)

Etsy has long had comprehensive observability over its machine learning (ML) deployments from a software engineering perspective.... (more…)

Machine learning operationalization has come to be seen as the industrial holy grail of practical machine learning. And that isn’t a bad thing – for data to eventually be useful to orga… (more…)