A Comprehensive Survey of Belief Rule Base (BRB) Hybrid Expert system: Bridging Decision Science and Professional Services

Abstract

The Belief Rule Base (BRB) system that adopts a hybrid approach integrating the precision of expert systems with the adaptability of data-driven models. Characterized by its use of if-then rules to accommodate various types of uncertainty through belief degrees, BRB adeptly handles fuzziness, randomness, and ignorance. This semi-quantitative tool excels in processing both numerical data and linguistic knowledge from diverse sources, making it as an indispensable resource in modelling complex nonlinear systems. Notably, BRB's transparent, white-box nature ensures accessibility and clarity for decision-makers and stakeholders, further enhancing its applicability. With its growing adoption in fields ranging from decision-making and reliability evaluation in network security and fault diagnosis, this study aims to explore the evolution and the multifaceted applications of BRB. By analysing its development across different domains, we highlight BRB's potential to revolutionize sectors traditionally resistant to technological disruption, in particular insurance and law.