Volume 4 Issue 2



Abstract : Objective:To reduce the fraud claims in health insurances companies and to improve outcomes in health care industry Analysis:In the existing system,Apache hadoop and Apache hive is used for processing data,it is a batch processing syste m. In proposed system,Apache spark is used for processing streaming data. Findings:EHR record is used as data source,it contains unique id for patients across world,so it is very easy to detect fraud claim with help of patientid. Apache spark processing streaming data on regular basis. But in existing system Apache hadoop and Apache hive takes hours of time to process the stored data. Improvement:Rule based model machine learning algorithm is used for detecting and automating the fraud claim and Apache spark is used for fast processing data,so it is more accurate and fast.

Pages : 10-13

Downloads : 3255

Publication Date :

Modified Date : 2017-02-20

Cite/Export :

I. KARTHIKA , K. P. PORKODI , "FRAUD CLAIM DETECTION USING SPARK", IJIERT - International Journal of Innovations in Engineering Research and Technology, Volume 4 Issue 2, ISSN : 2394-3696, Page No. 10-13