Fraud in insurance companies
As According to Verma and Mani (2002) analytics can contribute in accompanying your enterprise technologies into a social networking era, Big Data and CRM to crack down on financial offenders. Verma and Mani (2002) highlighted that the increasing number of mobile devices and social media platforms are bringing significant transformations in the world of business including the insurance sector. The opportunities offered by this landscape for insurers are vast. The myriad of social networks and communities enable insurers to connect with their customers in a more efficient manner, which in turn aids contributes towards brand equity, ...view middle of the document...
Analytics help in building a genuine worldwide perspective of the anti-fraud efforts all over the enterprise. Such a perspective leads towards to effective fraud detection by linking associated information within the organization.
Fraud can occur at a number of source points:
Claims or surrender
Employee-related or third-party fraud
At the same time, insurance channel expansion is adding to the fragmentation of traceable information. Insurance-related activities can be done via mobile devices apart from the traditional online and face-to-face insurance. This can be acknowledged as an expansion to data warehouse in the insurance sector. Given more terrific channel diversification and the increment in areas where fraud can happen, it is essential for insurers to have enterprise level information data about their business and clients.
Analytics hold an important role in integrating data. Effective detection of fraud involves discovery abilities that could be manufactured by joining together data from different sources. Analytics also help in integrating internal data with third-party data that may have predictive value, such as public records. Data sources with derogatory attributes are however a list of public records that can be merged into a model. Examples include bankruptcy, liens, judgements, records for criminal, foreclosures, or even there is a change in address to indicate a variance in behaviour. However, having different types of third-party data have benefits in enhancing efficiencies such as review of appraisal information to determine if damages match description or loss or injuries being claimed. The most under-utilized data sources are medical bill review data. If the data is used in a model properly, therefore it is a gold mine for enterprises investigating for medical fraud. By showing all the anomalies, in making an addition to the other scoring engines or social network analysis will diminish the time an investigator or analyst trying to assemble all the pieces together in order to identify a fraudulent activity.
On the other hand, Durtschi et al. (2004) have been using Benford’s law as a tool for the detection of fraud in accounting data. Here, it doesn’t focus on the insurance sector, though Durtschi et al. (2004) mentioned accounting data, it can also refers to the insurance sector as such. The purpose behind choosing this particular method is mainly for the effective use of digital analysis. Digital analysis conducted on the transactional more than the aggregate data can eventually assist the auditors in going through different deeper and check the data thoroughly.
Using Elliptic curve based Signature Method to control fake paper based certificates
Cryptography indeed plays a very important in the quest of controlling fake paper base certificates according to Murthy et al. (2011). Confidentiality, integrity and...