https://towardsdatascience.com/how-to-design-better-metrics-9bad7bc8c875 읽게된 동기: karel 소개로 읽게 됨 요약Principle 1: A metric should be a good proxy of what you’re trying to measure.다르게 얘기하면... 'what you're trying to measure'를 알아야하는데... 이부분이 제일 어려운 듯. Principle 2: The metric should be easy to calculate and understand복잡한 분석이 안좋은 이유.1. 🤔 They are difficult to understand. -> 매번 물어봐야하고 까먹고 오용하고..2. 🧑..