Modeling Nonlinear Time Series Patterns of Supply Chain Disruptions on Share Price Based Upon Firms’ Account Giving and Nodal Position

Organizations recognize disruptions can occur within supply chain networks with possible negative consequences. Given that the many firms are public entities, such disruptions can be flagged by the investor community and pull share prices down. In hoping to mitigate stock price erosion, organizations often employ various account giving strategies. However, to properly mitigate disruptions, organizations need to understand how disruptions along supply chains and account giving employed affect share prices over time. In this study, we rely upon Artificial Neural Networks (ANNs) to study the patterns of share price fluctuations over time (80 trading days) based upon the position of the disruption within the supply chain and the communication strategy employed. Using ANN, we go beyond prediction to plot the complex nonlinear patterns over the 80 days post disruption. Through our analysis, we demonstrate that nonlinear ANN provides greater accuracy relative to linear models. Furthermore, a time series analysis provides companies and investors with a greater degree of precision to deploy time-based hedging strategies not only to minizine losses, but also to possibly turn the disruptions into financial opportunities