Apache Kylin: Simplify Machine Learning on Big Data
Apache Kylin is an open source analytical data warehouse that has made interactive big data analytics possible. It does so by combining data warehouse and big data technology and by providing a standard ANSI-SQL query interface and sub-second latency for petabyte-scale datasets. This solution has been widely adopted around the world. Kylin also enables self-service data analysis for machine learning applications. The integration with auto machine learning technology means that users don't need to be experts in big data and machine learning technology. Dong will introduce the architecture and demonstrate how Apache Kylin has simplified machine learning on big data and empowered each end-user to perform advanced self-service analytics.