Against Accuracy
Why a mere accurate classification rule may not meet your business needs. And why you should insist on a model that returns numeric scores for classification problems. (link)
“I don’t think that means what you think it means;” Statistics to English Translation, Part 1: Accuracy Measures
Scientists, engineers, and statisticians share similar concerns about evaluating the accuracy of their results, but they don’t always talk about it in the same language. This can lead to misunderstandings when reading across disciplines, and the problem is exacerbated when technical work is communicated to and by the popular media. […]