Risk Assessment Through Big Data: An Autonomous Fuzzy Decision Support System

Decision support systems (DSSs) are computer-based systems that support managers in making operational, tactical, and strategic decisions. DSSs have been built to assist with a wide range of applications; however, in this paper, we are primarily concerned with risk assessment, which helps decision-makers to evaluate the risk of events. In recent years, advancements in big data processing, artificial intelligence, and machine learning have provided new opportunities for businesses to use these technologies for risk assessment. Yet, using these techniques with massive unlabeled data in an uncertain situation is challenging. This paper presents an autonomous fuzzy decision support system (AFDSS) for risk assessment that uses advanced artificial intelligence, unsupervised learning, and fuzzy logic. The model learns from big data characterized by uncertainty and a lack of labels for maximum utility. In an innovative approach, fuzzy clustering first extracts events from big data. Then, the risks associated with those events are assessed via a fuzzy inference system. New events are subsequently predicted based on their similarity to previously evaluated events. Evaluations of AFDSS with a real-world insurance dataset containing 500,000 journeys by 2500 drivers show that the proposed model can consistently assess risk in the big data environment. These results were drawn from a sensitivity analysis where all input parameters were changed using optimistic, pessimistic, and neural strategies. Performance was good across all three categories.