MacroBase: Prioritizing Attention in Fast Data. Peter Bailis, Edward Gan, Samuel Madden, Deepak Narayanan, Kexin Rong, Sahaana Suri. SIGMOD 2017. Selected as “Best of SIGMOD 2017”. 2017. Project website.
MacroBase is a data analytics tool that prioritizes attention in large datasets using machine learning. It is an open-source Apache licensed Java codebase. Here is what I think of MB: highly optimized implementations of data transformation, classification and explanation operators that can find anomalies in metrics and explain them by highlighting disproportionately correlated attributes.