Ripple effect modelling of supplier disruption: integrated Markov chain and dynamic Bayesian network approach. Issue 11 (2nd June 2020)

• Record Type: Journal Article
• Authors: Hosseini, Seyedmohsen; Ivanov, Dmitry; Dolgui, Alexandre
• Is Part Of: International journal of production research. Volume 58:Issue 11(2020)
• Page Start: 3284
• Page End: 3303
• Publication Date: 2020-06-02
• Subjects: supply chain dynamics -- supply chain resilience -- supply chain risk management -- Bayesian methods -- Markov modelling -- ripple effect; Factory management -- Periodicals; 658.57
• DOI: 10.1080/00207543.2019.1661538
• Languages: English
• ISSNs: 0020-7543

Abstract

Abstract : The ripple effect can occur when a supplier base disruption cannot be localised and consequently propagates downstream the supply chain (SC), adversely affecting performance. While stress-testing of SC designs and assessment of their vulnerability to disruptions in a single-echelon-single-event setting is desirable and indeed critical for some firms, modelling the ripple effect impact in multi-echelon-correlated-events systems is becoming increasingly important. Notably, ripple effect assessment in multi-stage SCs is particularly challenged by the need to consider both vulnerability and recoverability capabilities at individual firms in the network. We construct a new model based on integration of Discrete-Time Markov Chain (DTMC) and a Dynamic Bayesian Network (DBN) to quantify the ripple effect. We use the DTMC to model the recovery and vulnerability of suppliers. The proposed DTMC model is then equalised with a DBN model in order to simulate the propagation behaviour of supplier disruption in the SC. Finally, we propose a metric that quantifies the ripple effect of supplier disruption on manufacturers in terms of total expected utility and service level. This ripple effect metric is applied to two case studies and analysed. The findings suggest that our model can be of value in uncovering latent high-risk paths in the SC, analysing the performance impact of both a disruption and its propagation, and prioritising contingency and recovery policies.