Description
Speaker: Melanie Goetz
Productionizing data science often involves a team of scientists prototyping a statistical model in a language like R followed by a team of engineers translating and rebuilding that model into a “production" language. However, with Python, it’s easy to have your Data Science team and your Engineering teams working together collaboratively in the same language. But how does a modular production data science pipeline in Python look? This talk will cover how the data science pipeline at Clover automatically turns messy health data into insights and decisions.
Speaker Bio Melanie Goetz is a Data Science Lead at Clover Health, a health insurance startup in San Francisco. She studied Linguistics and Math/CS at MIT and dropped out of a CS PhD at UPenn. Previously, she worked at Oracle on machine learning, at Klout on natural language processing, and at Twitter on big data ad munging.