Ripple effect modelling of supplier disruption: integrated Markov chain and dynamic Bayesian network approach

Abstract

The ripple effect could occur when a disruption in supplier base cannot be localised and its consequences propagate downstream the supply chain (SC) adversely affecting the performance. While stress-testing of SC designs and assessment of their vulnerability to disruptions in single-echelon-single-event setting is desirable and indeed critical for some firms, modeling 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 consideration of both vulnerability and recoverability capabilities at individual firms in the network. We construct a new model based on integrating Discrete-Time Markov Chain (DTMC) and Dynamic Bayesian Network (DBN) model to quantify the ripple effect. We use DTMC to model the recovery and vulnerability of suppliers. The proposed DTMC model is then equalized with a DBN model in order to simulate the propagation behavior of supplier disruption in the SC. Finally, we propose a metric that quantifies the ripple effect of supplier disruption on manufacturer in terms of total expected utility and service level. The ripple effect measure constructed is examined and tested using two case-studies. The findings suggest that our model can be of value in revealing latent high-risk paths in the SC, analysing the performance impact of both a disruption and its propagation, and prioritizing the contingency and recovery policies.

The rippled newsvendor: A new inventory framework for modeling supply chain risk severity in the presence of risk propagation

“…First, we designed a model that radically reshapes the traditional newsvendor model. While cost and profit are always 42 J o u r n a l P r e -p r o o f objectives of concern, today's modern supply chains have led supply chain managers to redirect their attention to supply chain disruption, risk propagation, and severity (Craighead et al, 2007;Ivanov et al, 2017a;Hosseini et al, 2019b). As far as we are aware, this is the first major study to clarify and measure the construct of risk severity through the lens of risk propagation and the ripple effect.…”

“…For over 60 years, the newsvendor model has been the bedrock of the design of various inventory policy and systems. Despite the thousands of papers that have been written on the matter, few have attempted to address a pressing concern in modern inventory systems: the presence of the ripple effect (Ivanov et al, 2014;Hosseini et al, 2019b). The ripple effect is defined as the spread of disruption and the resulting impact on performance throughout a supply network (Ivanov, 2017).…”

“…The common element in this body of work has been how one element on the supply chain is "connected" to another element of the supply chain. For example, Hosseini et al (2019b) used dynamic Bayesian networks with integrated Markov chains to study and quantify the ripple effect. Extending off of this notion, research has also uncovered optimal strategies for supplier selection and optimal order allocation (Hosseini et al, 2019c).…”

A Review of Methods to Study Resilience of Complex Engineering and Engineered Systems

“…BNs have been deployed in several applications of infrastructure system reliability [10]; [11]; [12]; [13]; [14], but their use in modeling resilience is underdeveloped in the literature. For example, [10] proposed a novel BN model using event log data for analyzing the lateness probability in port logistics.…”

Sourcing with recycled materials: a contingent sourcing model with supply unavailability and setup time uncertainty for ripple effect mitigation

“…In addition, the Bayesian network theory and game theory have also proven to be valuable tools for analysing supply chains/networks with disruptions (e.g. Ojha et al 2018;Gupta, Ivanov, and Choi 2020;Hosseini, Ivanov, and Dolgui 2020).…”