Decision trees to model the impact of disruption and recovery in supply chain networks
Abstract
Increase in the frequency of disruptions in the recent times and their impact have increased the attention in supply chain disruption management research. The objective of this paper is to understand as to how a disruption might affect the supply chain network - depending upon the network structure, the node that is disrupted, the disruption in production capacity of the disrupted node and the period of the disruption - via decision trees. To this end, we first developed a 5-tier agent-based supply chain model and then simulated it for various what-if disruptive scenarios for 3 different network structures (80 trials for each network). Decision trees were then developed to model the impact due to varying degrees of disruption, and the recovery time from these disruptions. Visual outputs of the developed decision trees are presented to better interpret the rules. Supply chain managers can use the approach presented in this work to generate rules that can aid their mitigation planning during future disruptions.