Skip to Main Content
Supply chain scholars have applied optimization techniques such as linear programming and mixed integer programming to solve a variety of supply chain management problems. Despite the advancement of optimization techniques, this approach has not been fully extended to addressing more complicated problems such as revenue maximization and stochastic dimension. In this research, we propose an alternative approach based on multi-agent and CBR in solving optimization problems. One advantage of this approach is that supply chain managers can take advantage of the benefits of supply chain models with less effort. We compare the performance outcomes of the prototype system with the optimization model using a variety of scenarios. The results of statistical analyses suggest comparable performance outcomes between the two approaches, proving the feasibility and viability of our model in providing solutions to supply chain managers.