Published inData Science at MicrosoftFundamentals of building with LLMs: Question & answer on any document with ChatGPT in 30 lines of…A general approach to querying a text document with ChatGPT or other Large Language Models using the OpenAI APIAug 15, 2023Aug 15, 2023
Published inData Science at MicrosoftCategorically: Don’t explode — encode!Read this article before you start preprocessing your data for tree-based models!Jun 27, 2023Jun 27, 2023
Published inData Science at MicrosoftThe hidden validation set you aren’t using …I love random forests. Really, I love all decision tree–based models. The concept of learning by partitioning is not only simple and…May 9, 20231May 9, 20231
Published inData Science at MicrosoftFive mistakes to avoid when modeling with imbalanced datasetsAnd what to try insteadJan 24, 202315Jan 24, 202315