Early-warning modeling for supply chain variations using neutral networks

Effective management of a supply chain requires the ability to detect unexpected variations at an early stage, which brings the possibility of taking preventive decisions to avoid or mitigate the variations. This paper proposes a methodology that captures the dynamics of the supply chain, predicts and analyzes future trends, and indicates modification in the supply chain parameters to reduce possible variations. System dynamics are used to capture the dynamics of supply chain and neural networks are used to analyze simulation results in order to predict changes so that an enterprise would have enough time to respond to any undesired situations. Optimization techniques based on genetic algorithms are applied to find the best setting of the supply chain parameters that minimize the variations. A case study of manufacturing industry is presented to illustrate the methodology.