The Design of Model Productionization Architecture in Data Science

Too Long; Didn't Read

A lot of companies struggle to bring their data science projects into production. It is mainly because there is a huge knowledge gap, data scientists understand model building well but lack productionizing skills. The simple reason is these skills are not taught on Youtube videos and are hardly being touched by data science courses or the Kaggle learning method. I proposed an architecture that is near-realtime (batch inference every 5mins), fallbacks to the last model update (backend fetches previous update results from s3), and shared a slack webhook simple alert route.

---