ClaimChain: Secure Blockchain Platform for Handling Insurance Claims Processing

Abstract

Insurance claims processing involves multi-domain entities and multi-source data, along with a number of human-agent interactions. Consequently, this processing is traditionally manually-intensive and time-consuming. Blockchain technology-based platforms for intelligent automation can significantly improve the scale and response time of claims processing. However, there is a need to secure such platforms against fraud (e.g., duplicate claims) and the loss of data integrity caused due to cyber-attacks (e.g., Sybil attack). In this paper, we propose a novel “ClaimChain”, a consortium Blockchain platform that transforms the state-of-the-art NICB/ISO database architecture approach through increased shared intelligence and participation of insurance companies. ClaimChain features include: (a) automation of insurance claim processing via implementation of a Blockchain infrastructure, (b) infrastructure-level threat modeling via attack tree formalism for data integrity attacks, and (c) application-level fraud modeling for identified prominent red flags through machine learning models and risk scoring on the basis of risk severity. We evaluate the scalability of ClaimChain by simulating realistically large number of Blockchain transactions of claim processing. Further, we show that data integrity attacks at the infrastructure-level can be mitigated (as seen in reduction of 24% probability in loss) through implementation of security design principles. We also perform fraud-detection over an open dataset in ClaimChain to show how machine learning models can detect fraudulent activity with 98% accuracy.