Loading…
  • 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

View analytic
Wednesday, March 21 • 4:30pm - 5:00pm
Anomaly Detection in Medicare Provider Data using OAAgraph

Log in to save this to your schedule and see who's attending!

Feedback form is now closed.
Graph analysis is an effective methodology in data analysis which considers fine-grained relationships between data entities. This session presents an example of anomaly detection using graph analysis on data stored in Oracle Database with Oracle R Enterprise and the OAAgraph package, using a real-world public data set.
Specifically, we analyze the public information of medical transactions from CMS (United States Center for Medicare and Medicaid Services) for the year 2012. We load this data set as a graph into Oracle Database, and use the OAAgraph package to apply graph analysis algorithms whose results are be visualized using R's ggplot2 visualization package. 
Our analysis successfully identifies suspicious records in the data set -- medical providers who perform procedures far from their specialties. We also discuss techniques how to reduce false positive outcomes. 

Speakers
avatar for Sungpack Hong

Sungpack Hong

Research Manager, Oracle
Research Director at Oracle Labs.Leading projects regarding large-scale graph and data analysis -- platforms and applications
avatar for Mark Hornick

Mark Hornick

Director, Advanced Analytics and Machine Learning, Oracle
FM

Francisco Morales

Software Developer, Oracle Labs


Wednesday March 21, 2018 4:30pm - 5:00pm
2-Rm 102

Twitter Feed