A data-driven Bayesian model for evaluating the duration of detention of ships in PSC inspections

Abstract

Port State Control (PSC) inspections are essential for port authorities to improve vessel quality and ensure maritime safety worldwide. However, the increasing frequency and duration of ship detentions indicate serious deficiencies of visiting vessels still largely exist, highlighting the urgent need for scientific solutions. This research aims to improve the efficiency of inspection policy and reduce the duration of detention by developing a data-driven Bayesian Network (BN) model using an improved machine-learning (ML) based methodology. New risk variables influencing the duration of ship detention, especially deficiency types, are identified based on the established database containing detention records within the jurisdiction of the Paris MoU from January 2015 to March 2022. Thorough analysis using the developed model allows the identification of deficiency types with a significant impact on the duration of detention, the discovery of interdependencies between these types and the clarification of the major and abnormal deficiency types in different port states. Policy implications and managerial recommendations for port authorities are presented. These include developing clear instructions on types of deficiencies that significantly impact detention time and proposing a selection strategy for vessels in different countries based on their specific circumstances. The proposed model utilizes big data analytics to support the development of inspection policies that are rational and effective. This research will provide good reference for effectively reducing the duration of ship detention, providing policy recommendations, improving ship standards, and ensuring maritime safety.