Fraudulent claims have long been a challenge for insurance firms. Currently, it is estimated that around 10% of short-term insurance claims are fraudulent, but fewer than 20% of those are detected, amounting to millions lost to fraud annually.
Traditional fraud detection methods, such as relying on experienced staff to process claims, are no longer effective enough. This is increasingly the case with growing numbers of clients and massive increases in the volume of data available. With resources at a premium, insurers can quite simply not allocate sufficient human resources to sift through and collate data from multiple sources and interpret them in ways that deliver business value. In addition, because fraudsters are smart people and constantly change their patterns, simply hard-coding rules in claims processes is not the answer.
The solution lies in high performance analytics, which makes it possible for insurers to find patterns both in the data residing in their own data warehouses, and also in related external data, such as public records. By building a global perspective of related information, advanced analytics enables insurers to better identify fraudulent claims and even predict where potential risks lie. Third party data that can be valuable in contributing to fraud identification might include data on bankruptcies, litigation, address change velocity or even medical bill review data. A wealth of information also resides in unstructured sources, including social networks.
With advanced predictive analytics, insurers are able to organise and analyse both structured and unstructured data to deliver more accurate assessments of fraud risk and even the potential for future fraud attempts. By streamlining fraud assessment, predictive analytics reduces fraud losses and also speeds up claims processing, which results in a better customer experience. In fact, the overall return on investment is quite staggering.
Enabling these advanced capabilities requires redesigning the data warehouse environment. In order to harness, process and analyse massive volumes and varieties of data in near real time, big data processing becomes critical. The potential cost and time to value of this exercise is what holds many insurers back in adopting high performance analytics tools. However, with new distributed computing options like in-memory processing on commodity hardware, insurers can have access to a flexible and scalable real-time big data analytics solution at a reasonable cost. And the resulting financial returns and competitive benefits cannot be ignored.
High performance analytics is not just another technology fad - it is a revolutionary tool that delivers a measurable ROI and improves competitiveness and customer satisfaction.
