Strange Loop

Zipline - A Declarative Feature Engineering Library

Zipline is Airbnb's data management platform specifically designed for ML use cases. Previously, ML practitioners at Airbnb spent roughly 60% of their time on collecting and writing transformations for machine learning tasks. Zipline reduces this task from months to days - by making the process declarative. It allows data scientists to easily define features in a simple configuration language. The framework then provides access to point-in-time correct features - for both - offline model training and online inference.

In this talk we will describe the architecture of our system and the algorithm that makes the problem of efficient point-in-time correct feature generation, tractable.

Nikhil Simha

Nikhil Simha


Nikhil is a Software Engineer on the Machine Learning infrastructure team at Airbnb. He is currently working Bighead, an end-to-end machine learning platform. Prior to Airbnb, he worked on schedulers, resource managers, real-time data processing engines and compilers. He is also the co-author of Realtime Data Processing at Facebook (SIGMOD-16). Nikhil got his Bachelors degree in Computer Science from Indian Institute of Technology, Bombay. While not working, he likes to boulder or play capoeira.