Intelligent system based support vector regression for supply chain demand forecasting

Supply chain management (SCM) is an emerging field that has commanded attention from different communities. On the one hand, the optimization of supply chain which is an important issue, requires a reliable prediction of future demand. On the other hand, It has been shown that intelligent systems and machine learning techniques are useful for forecasting in several applied domains. In this paper, we introduce the machine learning technique of time series forecasting Support Vector Regression (SVR) which is nowadays frequently used. Furthermore, we use the Particle Swarm Optimization (PSO) algorithm to optimize the SVR parameters. We investigate the accuracy of this approach for supply chain demand forecasting by applying it to a case study.