• Sessions appear in the color of their primary track
  • Sessions can be filtered using Products on the right
  • Use the Search bar for more flexibility
See this link for hints on how to search the schedule or sign up for sessions
Back To Schedule
Thursday, March 22 • 8:45am - 9:35am
New Machine Learning capabilities: Interacting with Spark DF in ORAAH
Feedback form is now closed.
The newly redesigned ORAAH (Oracle R Advanced Analytics for Hadoop) brings a complete rewrite of it's I/O model, allowing for the use of a complete in-memory pipeline, from data transformation and loading all the way to Machine Learning models and predictions. In addition to that, a new transparency layer to Impala, plus the option to run HIVE on Spark queries, can keep the data always in-memory across different platforms. A new Extreme Learning Machine algorithm will be introduced, and enhancements on the Logistic and Linear Regression algorithms will increase scalability even more. Benchmarks with the new features will be presented on typical use cases by customers, from predicting flight cancellations and delays to Image Classification.

avatar for Marcos Arancibia

Marcos Arancibia

Product Manager, Oracle Data Science and Big Data, Oracle
Marcos Arancibia is the Product Mgr for Oracle Data Science and Big Data, working with Machine Learning in the Oracle Database and on Hadoop/Spark clusters. He is charted with developing a comprehensive platform for enabling a new class of analytical workloads encompassing techniques... Read More →

Thursday March 22, 2018 8:45am - 9:35am PDT