A fuzzy knowledge-based system for premium rating of workers' compensation insurance for building projects

Abstract

Occupational injuries and fatalities are rampant in construction. The significance of the workers' compensation insurance (WCI) is immeasurable in safeguarding the interests of construction workers and contractors. From the insurers' perspective, the commitment under this insurance is extremely broad; there are no exclusions and a maximum limit on their liability. Thus, insurers must accomplish rigorous risk and market assessments to decide optimal premiums for construction projects. The conventional experience rating approach of premium rating has been proven ineffective for construction applications. Based on the findings of a literature review and an interview questionnaire survey, a new WCI premium rating model was developed for building projects. A hybrid of interviews and past workers' compensation claims data analysis was adopted to develop the conceptual model of a fuzzy knowledge-based system (KBS) to automate the proposed model. It was then prototyped, and verified with Turing tests. The proposed model and its fuzzy KBS advocate real time structured assessments of project hazards, safety, market condition and insurers' internal factors for premium rating. They also establish an effective risk control strategy via a well-structured incentive system for contractors and clients. Their implementation in the general insurance industry can facilitate accident control in the construction industry, thereby minimizing insurers' financial risks.