Wanlop Fuangfoo.. Demand forecasting for export and import warehouse by using artificial neural network : a case study of pharmaceutical warehouse. Master's Degree(Industrial Engineering). Mahidol University. Mahidol University Library and Knowledge Center. : Mahidol University, 2014.
Demand forecasting for export and import warehouse by using artificial neural network : a case study of pharmaceutical warehouse
Abstract:
Import or Export Warehouses are comparative distribution centers of international trade. In order to be managed, these warehouses face plenty of challenges and complications, above typical domestic ones. In the receiving and put away process, it takes a long time of approximately 70% of the total operation time. This is due to the fact that a lack of information about the actual amount of incoming products being received. Hence, the main purpose of this research study is to find an appropriate forecasting model in order to estimate the actual incoming products received, that is suitable for an import and export warehouse. This study highlights only medical devices or pharmaceutical products as the representative case samplings because in terms of market sectors, medical or pharmaceuticals contribute 1 out of 6 sections of the total national consumer goods. This research used 3 methodologies comparatively; Time Delay Neural Network (TDNN), Box-Jenkins Model (ARIMA), and Hybrid Model. The study defined that the TDNN model provides the best accuracy in forecasting, indicated by the least deviation. The model provides the most accurate results against the other models. Therefore, with efficiency forecasting model development, the processing time in a warehouse is reduced by 22%, and the cost of the operation of the activities is reduced by 20%.