Gray relation analysis and multilayer functional link network sales forecasting model for perishable food in convenience store

In managing convenience store, making the right decision in placing a balanced order is a critical job that can enhance the competition of the corporation, especially in perishable food. In this study, the GMFLN forecasting model integrates Gray relation analysis (GRA) which sieves out the more influential factors from raw data then transforms them as the input data in the multilayer functional link network model to provide the more accurate forecasting results to support the decisions. The proposed system evaluated the real data, which are provided by famous franchise company, and the experimental results indicated the GMFLN model outperforms than other different time series forecasting models, i.e. the moving average model, ARIMA model and GARCH model in MAD and THEIL indexes.