Feed-forward neural network forecasting : a case study | |
| Author | Ho Trung Thao |
| Call Number | AIT Thesis no.ISE-02-11 |
| Subject(s) | Neural networks (Computer science)--Forecasting Sale of business enterprises Computer algorithms |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Advanced Technologies |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. ISE-02-11 |
| Abstract | In today's dynamic and turbulent business environment, there is a strong need for the organization to become globally competitive. The survival guide to competitiveness is to be closer to the customer and deliver value added product and services in the shortest possible time. This, in turn, demands integration of business processes of an enterprise. Enterprise Resource Planning (ERP) is such a strategic tool, which helps the company to gain competitive edge by integrating all business processes and optimizing the resources available. The ERP approach includes an integrated set of techniques used to create time-phased production and procurement plans of the raw materials and components. These detailed plans for both the quantity and timing of requirements are based on desired end item (e.g. finished goods) availability, driven by -an important input- Master Production Schedule (MPS). A case study can gives a good picture of future improvement in implementation and use of ERP. For a better demand prediction in Master Production Schedule, a feed-forward neural network based demand (sale) forecast model - is built with Visual Basic to support the Intuitive ERP package. This research has been performed in three steps: First, sales data collection in the TTT company has been carried out. Second, a feed forward back-propagation neural network algorithm for forecasting has been developed. In this step, a preliminary capacity compadson between traditional methods and neural network model has been carried out. Lastly, sale forecasting with the feed forward neural network package has been built. |
| Year | 2002 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. ISE-02-11 |
| Type | Thesis |
| School | School of Advanced Technologies (SAT) |
| Department | Department of Industrial Systems Engineering (DISE) |
| Academic Program/FoS | Industrial Systems Engineering (ISE) |
| Chairperson(s) | Bohez, Erik L. J.; |
| Examination Committee(s) | Voratas Kachitvichyanukul;Manukid Parnichkun;Huynh Trung Luong; |
| Scholarship Donor(s) | Asian Institute of Technology Partial Fellowship; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 2002 |