Application of Bayesian networks in analysing tanker shipping bankruptcy risks

Purpose: This study aims to develop an assessment methodology using a Bayesian network (BN) to predict the failure probability of oil tanker shipping firms. Design/methodology/approach: This paper proposes a bankruptcy prediction model by applying the hybrid of logistic regression and Bayesian probabilistic networks. Findings: The proposed model shows its potential of contributing to a powerful tool to predict financial bankruptcy of shipping operators, and provides important insights to the maritime community as to what performance measures should be taken to ensure the shipping companies’ financial soundness under dynamic environments. Research limitations/implications: The model and its associated variables can be expanded to include more factors for an in-depth analysis in future when the detailed information at firm level becomes available. Practical implications: The results of this study can be implemented to oil tanker shipping firms as a prediction tool for bankruptcy rate. Originality/value: Incorporating quantitative statistical measurement, the application of BN in financial risk management provides advantages to develop a powerful early warning system in shipping, which has unique characteristics such as capital intensive and mobile assets, possibly leading to catastrophic consequences.