Abstract

Machine Learning (ML) is a critical component of several novel applications and intelligent features in existing applications. Recent advances in deep learning have fundamentally advanced the state-of-the-art in several areas of research and made it easier to apply ML to a wide variety of problems. However, applied ML projects in industry, where the objective is to build and improve a production feature that uses ML, continues to be complicated and often bottlenecked by data management challenges. ItemSuggest is a platform for building contextual relevance services. In this paper, we describe ItemSuggest with a focus on how we leverage key ideas from data management to make it dramatically easier to build machine-learned ranking services. The platform allows engineers to focus on application-specific modeling and simplifies key tasks of 1) gathering training data; 2) cleaning, validating, and monitoring data quality; 3) training and evaluating models; 4) managing the feature lifecycle; and 5) running A/B tests. We outline key design choices anchored around the core idea of optimizing for experiment velocity. We describe lessons learned from applications built on this platform that have been in production serving hundreds of millions of users for over a year. Finally, we identify two key components of the platform where data management research can have a major impact—a transformation engine for feature engineering and one for training set representation. We believe such platforms have the potential to accelerate and simplify ML applications the same way data warehouses radically simplified complex reporting applications.