End-to-End Data Science to Drive Business Decisions at LinkedIn with Burcu Baran - TWiML Talk #256
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Navigating Data Science: Debugging and Model Training
This chapter explores the critical debugging process in data science, emphasizing manual checks and automated functionalities in label preparation. It discusses the iterative modeling approach, complexity of defining outcomes in classification tasks, and the balance between model interpretability and performance. Additionally, it highlights the importance of data partitioning and the strategies used at LinkedIn to ensure that models are built on relevant, time-sensitive training data.
Transcript
Play full episode
