Balanced-Sampling-Based heterogeneous SVR ensemble for business demand forecasting
ICIC'11 Proceedings of the 7th international conference on Advanced Intelligent Computing
| Hi-index | 0.00 |
Demand forecasting plays a crucial role for supply chain management of retail industry. The future demand for a certain product constructs the basis of its relevant replenishment system. In this research, the technique of Support Vector Machine (SVM) is employed for demand forecasting. Various factors that affect the product demand such as seasonal and promotional factors have been taken into consideration in the model. Meanwhile, different other approaches such as Statistical Model, Winter Model and Radius Basis Function Neural Network (RBFNN) are also used for comparison and evaluation. The experiment results show that the performance of SVM is superior to other models, which will lead simultaneously to fewer sales failure and lower inventory levels.