Intelligent multivariate sales forecasting using wrapper approach and neural networks

Abstract

This research investigated a retail sales forecasting problem based on early sales. An effective multivariate intelligent decision-making (MID) model is developed to handle this problem by integrating a data preparation and preprocessing module, a harmony search-wrapper-based variable selection (HWVS) module and a multivariate intelligent forecaster (MIF) module. The HWVS module selects out the optimal input variable subset from given candidate inputs as the inputs of MIF. The MIF is proposed to model the relationship between the selected input variables and the sales volumes of retail products, and then employed to forecast the sales volumes of retail products. Experiments were conducted to evaluate the effectiveness of the proposed model. Results show that it is statistically significant that the proposed MID model can provide superior forecasts to ELM-based model and generalized linear model.