Analysis of inventory routing problem with simulation and big data approach

In supply chain environments, inventory and routing are key elements to company's survival and sustainability. Unsatisfactory inventory control and routing will hurt company profitability and market competitiveness. Therefore, the solution of inventory routing problem (IRP) should provide optimal inventory level for each supply chain member and also obtain efficient route that minimizes the routing cost over periods. At this point, hybrid methodology can empower analyst to minimize the risk and cost of the changes in the IRP. In this paper, new hybrid methodologies that include two parts are developed to solve the IRP. In the first part, a new hybrid method including simulation optimization and artificial intelligence based simulation is created to solve the IRP in which three different routing strategies are evaluated for uneven demand patterns including intermittent, erratic, and lumpy demand. In the second part, big data and sentiment analysis are used to transform customer reviews into meaningful information and to create value. Then, artificial intelligence and simulation optimization are employed to analyze the IRP. Numerical results proposed by the hybrid methodologies showed that dynamic and stochastic IRP can be successfully solved when the method is properly set up.