dssg / triage

What it does

Building ML/Data Science systems requires answering many design questions, turning them into modeling choices, which in turn define and machine learning models. Questions such as cohort selection, unit of analysis determination, outcome determination, feature (explanatory variables or predictors) generation, model/classifier training, evaluation, selection, bias audits, interpretation, and list generation are often complicated and hard to make design choices around a priori. In addition, once these choices are made, they have to be combined in different ways throughout the course of a project.