Bloomington, IN – April 16, 2010. Megaputer Intelligence will be presenting at the The Computer Forensics Show in New York, New York on April 20, 2010
TRACK: Forensic Accounting
DATE: Tuesday April 20, 2010
TIME: 1:20-2:35pm
SESSION TITLE: Data and text analytics for insurance fraud detection and e-Discovery
Financial transactions and electronic communications leave a broad trace of data recorded in electronic storage systems. This data holds relevant evidence enabling investigators discover fraud and abuse. Yet, investigators frequently get overwhelmed by huge volumes of data they have to process. It is not practical to manually analyze every claim received by a healthcare company or every email letter sent by employees of a large company in the context of all other transactions. Investigators are seeking more automated tools that can process huge volumes of data to detect anomalous behavior patterns and to investigate whether these anomalies indeed represent cases of fraud and abuse.
The workshop presents the results of a fraud detection and engineering quality enhancement project based on the data and text mining of the product warranty and repair data from an automotive manufacturer. It outlines the challenges the manufacturer was facing, and discusses the data, analysis methodology, obtained results, and their business value. The presented material will be of interest to warranty, quality, and product managers, corporate executives, and other decision makers.
Traditional data analysis systems based on targeted queries and statistical analysis techniques provide some automation of investigations, but they provide little guidance on where investigators should initially concentrate their efforts. The majority of investigations are still launched only after receiving a tip from whistle blowers. A new generation of data and text mining software tools based on advanced machine learning and natural language processing techniques can reveal anomalous patterns in data and enable investigators to focus their efforts on the analysis of key potential problems. These tools perform systematic analysis of huge volumes of data to determine typical behavior patterns and trends, discover anomalies, and help investigators determine the nature of fraud and abuse patterns.
Dr. Ananyan will present three fraud detection cases performed with the help of data and text mining tools. The first two cases deal with insurance fraud detection. One case illustrates how advanced analysis of piles of structured data representing health insurance claims can reveal anomalous patterns tying together patients, providers, diagnoses, procedures and their financial characteristics. The second case outlines how investigators working on property and casualty insurance cases can derive important new insights from automated analysis of free-text notes associated with the considered claims. The third case discusses the use of text mining tools for monitoring corporate email communications to ensure systematic fraud detection and policy compliance.
About Megaputer Intelligence
Megaputer Intelligence is a leading developer of data and text mining software offering tools for predictive modeling and knowledge discovery in large volumes of structured data and text. Megaputer analytical tools enable over 500 customers worldwide to make informed data-driven decisions.
About the Computer Forensic Show, LLC and The New York Metro InfraGard
InfraGard is a partnership for the protection of our nation’s critical infrastructures from terrorism and related criminal activity through information sharing and analysis. It is a collaborative effort between the Federal Bureau of Investigation (FBI), other Federal, state and local law enforcement, government, academic, and private sector experts focusing on physical and cyber security, and risk management. On a national level, InfraGard is a network of over 33,000 FBI-vetted industry professional volunteers serving as critical infrastructure subject matter experts in one or more sectors.
Megaputer and PolyAnalyst are registered trademarks of Megaputer Intelligence Inc. in the United States and/or other countries. The names of other companies and products mentioned herein may be the trademarks of their respective owners.
For more information:
Richard Kasprzycki
Megaputer Intelligence, Inc.
(812) 330-0110 ext 201
rkasprzy@megaputer.com