Files
Abstract
Healthcare is a billion dollar industry in United States and worldwide. According to Institute of Medicine, almost 30 cents of any medical dollar, is either wasted due to abuse, fraud, or waste, or due to paperwork, unneeded and unnecessary services. Big Data nowadays gives us solutions to analyze, predict and make decisions. The datasets publicly available gives us the opportunity to expose the data to analytic power of Big Data which let us discover new aspects of data. Our goal is to develop a Hadoop Statistics engine, to receive the large public health datasets as an input and deliver a descriptive, more meaningful interpretation of the data to be prepared as an input to predictive and decision engines. The main goal of our engine is to detect anomalies and fraudulent behaviors among our healthcare data according to statistic measures, however it can be further utilized by any type of large dataset as a Big Data Descriptive engine.