Demand forecasting in a Supply Chain using Machine Learning Algorithms

Abstract

Abstract—the purpose of this paper is to compare two artificial intelligence algorithms for forecasting supply chain demand. In first step data are prepared for entering into forecasting models. In next step, the modeling step, an artificial neural network and support vector machine is presented. The structure of artificial neural network is selected based on previous researchers' results. For measuring errors we use Mean squared error and we use another index for time which is used running the algorithms. The results show that artificial neural network can forecast more accurate meanwhile support vector machine is faster.

Keywords

• artificial neural networks (ann)
• bullwhip effect
• demand forecasting
• support vector machine (svm)