In the early days of personalization, the focus was on smarter, more complex machine learning models, on algorithms and optimizations. Later, the attention shifted to feature engineering as a driver for accuracy. Finally, the community focused on data as the next frontier: volume, quality, cleansing, and clean labeling. In this talk, we focus on the crucial next step in personalization: well designed software architectures for storing, computing, and delivering responsive, accurate in-...

Today, tooling for ad-hoc data science is fairly well understood. But when you want to create a repeated process such as analytics or prediction systems, things tend to change with time, and how to deal with such change is not always clear. Columns and features are added and removed. New models are developed. Data errors are discovered and corrected. How can we build a data pipeline system to handle these demands? This talk will discuss some of the systems challenges and solutions that arise...