By using data smartly, using sophisticated algorithms to combine datasets and detect connections and patterns using visualization tools, service providers of micro-insurance and medical aid products can effectively mitigate their fraud risk. The need for a real-time identification, response and prevention (data-to-decision process) of fraud is essential to reduce the insurer’s fraud exposure. Layering data modelling onto various forms of customer data, exception reporting, financial trends, geospatial data and historic fraud data, it becomes possible to predict which customers have a higher propensity to commit fraud at claims stage. Effective machine learning fraud models aims to more accurately identify fraudulent claims, greatly reducing the number of false positive investigations. The fraud models also allow quick overview on low risk claims, allowing these claims to be paid as quickly as possible and without any client inconvenience.
As an example of processing large data sets effectively, findings of a study done on an international medical aid scheme revealed several impossible claims. Patients were treated for smallpox, a disease that has been completely eradicated, with the last known case in 1949 in the United States. In the same study high volume of dental treatment of toddlers raised red flags. Similarly, a high volume of claims pertaining “Leomyoma of Uterus” were flagged and after analysis all claims regarded as suspicious, seeing that a portion of them were performed on male patients, an obvious impossibility. A ratio between paid and unpaid claims were calculated and the severe anomaly were analysed and found that all the treatments for breast cancer and uterine bleeding were for males.
In short, companies that can leverage off the swing towards micro-insurance and similar medical aid products, and create simple, flexible solutions to customer needs supported by effective risk mitigation tools will be at the forefront of this innovation revolution.