About
R is fast becoming the lingua franca for analyzing data via statistics, visualization, and predictive analytics. For enterprise-scale data, R users have three main concerns: scalability, performance, and production deployment. Oracle's R-based technologies - Oracle R Distribution, Oracle R Enterprise, Oracle R Connector for Hadoop, and the R package ROracle - address these concerns.
In this talk, we introduce Oracle's R technologies, highlighting how each enables R users to achieve scalability and performance while making production deployment of R results a natural outcome of the data analyst/scientist efforts. The focus then turns to Oracle R Enterprise with code examples using the transparency layer and embedded R execution, targeting massive predictive modeling. One goal behind massive predictive modeling is to build models per entity, such as customers, zip codes, simulations, in an effort to understand behavior and tailor predictions at the entity level. Predictions can then be aggregated, for example, to assess future demand. Massive predictive modeling comes with challenges: effectively partitioning data, where to store and manage the resulting models, how to associate models with customers, as well as backup, recovery, and security.
While R has parallel capabilities to facilitate taking advantage of clusters of computers, significant coding is usually required to meet the challenges noted above. In this talk, we present the business problem and illustrate how Oracle R Enterprise, one of Oracle?s R technologies, facilitates massive predictive modeling in a pair of succinct R scripts. With Oracle R Enterprise, the data, R scripts, and models all reside in Oracle Database.
About the speaker
Mark Hornick, Director, Oracle Advanced Analytics, focuses on Oracle's R Technologies. He works with internal and external customers in the application of R for scalable advanced analytics applications in Oracle Database, Exadata, and the Big Data Appliance. Mark is…
The talk
Credits and licence
- Institution
- CERN
- Department
- Computing Seminar
- Speaker
- Mark F. Hornick
- Year
- 2014
- Language
- English
- Subjects
- Computer science
- Source
- CERN
- Licence
- CERN, as CERN states it. CERN's terms
- Attribution
- © CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
- Who can watch
- CERN gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed