MacroBase: Prioritizing Human Attention in Big Data

Abstract: MacroBase is a new analytic monitoring engine designed to prioritize human attention in large-scale datasets and data streams. Unlike a traditional analytics engine, MacroBase is specialized for one task: finding and explaining unusual or interesting trends in data. With its unique feature selection functionality, MacroBase has found and explained the cause of previously unknown behaviors in several domains, including online services, mobile devices, user analytics, automotive telemetry, and manufacturing.

In this workshop, we’ll describe how to write MacroBase queries and analyze your own data using MacroBase SQL, an extension of SQL that incorporates our new MacroBase operators. We’ll also show how to query large-scale datasets using MacroBase SQL on Spark, our distributed version of MacroBase that integrates seamlessly with other Spark APIs. We’ll provide sample datasets to play with, but we highly encourage you to bring your own datasets to analyze with MacroBase!

MacroBase is an ongoing research project in the Stanford FutureData Systems Group and the Stanford DAWN Project—for more information, check out Installation instructions can be found at

Bio: Coming Soon

Open Data Science Conference