ABSTRACT
The semi-structured and un-structured data are stored in Big Data databases such as HIVE. A Big Data use case provides a focus for analytics, providing parameters for the types of data that can be of value and determining how to model that data using Hadoop analytics. The insurance industry is taking the lead in this regard. Many insurers analyze their internal data, such as call center notes and voice recordings, alongside social media data and third party details on people's bills, wages, bankruptcies, criminal records, and address changes to gain insight into potentially fraudulent claims. The insurance sector has traditionally analyzed fraud data in silos and largely ignored un-structured data points, but this is changing. For pre-emptive fraud prevention, it is important to be able to capture potential fraud patterns, which can then be used advantageously over and over again. These are some of the challenges for the insurance industry.
