Please use this identifier to cite or link to this item:
|Title:||Adopting a hierarchic metric approach for supporting demand forecasting||Authors:||Woo, Sheng Yao.||Keywords:||DRNTU::Engineering::Systems engineering||Issue Date:||2009||Abstract:||The objective of the project was to design a systematic framework for decision makers to represent the possible factors affecting demand forecasting. The hierarchic metric approach, Analytical Hierarchic Process (AHP), which is a qualitative based forecasting technique, will be used as a tool to support demand forecasting. This report will begin with an introduction to demand forecasting and its applications. The forecasting techniques which include the quantitative and qualitative approach will be presented in this report. In this report, a hierarchic metric approach, the Analytical Hierarchy Process, will be adopted as a tool to analyze the criteria affecting the forecast of demand. In addition, this approach will be performed on a case study (Forecasting the demand of global oil consumption) to illustrate how this approach works. The Expert Choice software, which is based on the Analytical Hierarchic Process, will be used to construct the hierarchic structure that represents an overview of the various criteria that influence the demand forecast of global oil consumption. A brief description of each criteria identified will be discussed in this report. Pair-wise comparison, which is based on the decision maker‟s personal judgment, will be performed on the criteria and alternatives to determine their relative importance or likelihood The Expert choice software enables the priority values of the factors and alternatives to be easily calculated. These priority values allow the decision maker to determine the most likely alternatives with respect to the goal of forecasting upon synthesis of the results. Lastly, sensitivity analysis can be performed on the criteria to determine how changing the priority values of the criteria affects the priority values of the alternatives and consequently the rank order of the alternatives‟ likelihood with respect to the goal of demand forecasting. The results obtained from the performance and gradient sensitivity analysis will be presented in this report.||URI:||http://hdl.handle.net/10356/17190||Rights:||Nanyang Technological University||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||MAE Student Reports (FYP/IA/PA/PI)|
checked on Sep 30, 2020
checked on Sep 30, 2020
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.