Using Bayesian network-based TOPSIS to aid dynamic port state control detention risk control decision

Port State Control (PSC) inspections have been implemented as an administrative measure to detect and detain substandard ships and thus to ensure maritime safety. Advanced risk models were developed to investigate the impact of factors influencing ship detention. Although showing much attractiveness, current studies still reveal a key challenge on how such analysis can improve the ship performance in PSC inspections and aid PSC detention risk control decision. By incorporating a data-driven Bayesian network (BN) into the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method, this paper proposes a new ship detention risk control methodology, in which the decision criteria are generated from the root risk variables, and the alternatives refer to the established strategies adopted by ship-owners in their practical ship detention risk control. Along with the new methodology, the main technical novelty of this paper lies in the quantitative measurement of the effectiveness of each strategy in terms of the reduction of detention rate in a dynamic manner. Its practical contributions are seen, from both ship owner and port authority perspectives, through the provisions of useful insights on dynamic evaluation of rational control strategies to reduce ship detention risk under various PSC inspection scenarios.