Risk analysis of cargo theft from freight supply chains using a data-driven Bayesian network

Cargo theft has been among the most concerning risks influencing global freight supply chains, which causes serious supply chain disruptions, injuries/deaths, economic loss, and environmental damage. However, there are very few studies on the risk analysis of cargo theft, particularly in a quantitative manner, and fewer on the relevant risk factors affecting theft-related accidents in the current literature. This paper aims to analyse the risk influential factors (RIFs) of cargo theft and predict the occurrence likelihood of different types of cargo theft accidents. The historical data of 9316 cargo theft accidents that happened in the UK from 2009 to 2021 were first collected from the TAPA IIS database, and then purified and trained to construct a Bayesian network (BN) based cargo theft risk analysis model. The data-driven BN interprets the interdependency of RIFs and their combined effects on the occurrence of different types of cargo theft accidents. Compared with the previous studies, this paper makes new contributions, including that (1) The cargo theft RIFs are identified from the literature and accident records. (2) A data-driven BN is proposed to construct the model with uncertainty to realise cargo theft risk prediction and diagnosis. (3) The critical RIFs contributing to cargo theft are evaluated and prioritised to predict the occurrence of possible cargo theft accidents. (4) The real accidents are investigated to verify the model and draw useful insights for cargo theft prevention. The findings show that the most influential RIFs for the occurrence of cargo theft accidents are product category, year, location type, modus operandi (MO), and region. The findings also reveal the combined risk contributions of the RIFs, hence providing useful insights for cost-effective theft risk control in practice.