A Poisson-Regression, Support Vector Machine and Grey Prediction Based Combined Forecasting Model Proposal: A Case Study in Distribution Business

Abstract

Demand forecasting is a complicated task due to incomplete data and unpredictability. Accurate demand forecasting has a direct impact on the performance of a company. The goal of the study is to present a new two-stage combination model named Hybrid-2-Best, for accurate demand forecasting. The model combines three forecasting models in a single combined forecast. The Hybrid-2-Best model uses a two-stage algorithm to achieve better-performing forecasts. Case study showed that the proposed Hybrid-2-Best model performs the best forecast performance among other combination techniques and individual methods. Furthermore, GP integration in the first and second stages gives flexibility. Experimental results indicate that the proposed Hybrid-2-Best model is a promising alternative for sales demand forecasting. MAPE of the proposed model is 0,13. This is a good result and better than compared other models. Proposed model performed better than other compared models in MASE and MSE as well