Tuesday, November 8th, 2011
WibiData is a collaborative data mining and predictive modeling platform for large-scale, multi-structured, user-centric data. It leverages HBase to combine batch analysis and real time access within the same system, and integrates with existing BI, reporting and analysis tools. WibiData offers a set of libraries for common user-centric analytic tasks, and more advanced data mining libraries for personalization, recommendation, and other predictive modeling applications. Developers can write reusable libraries that are also accessible to data scientists and analysts alongside the WibiData libraries. In this talk, we will provide a technical overview of WibiData, and show how we used it to build FoneDoktor, a mobile app that collects data about device performance and app resource usage and offers personalized battery/performance improvement recommendations directly to users.