王福琨952221E011137MY3(第1年)

王福琨952221E011137MY3(第1年)

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
行政院國家科學委員會補助專題研究計畫期中精簡報告 產業階層式先進規劃排程 子計畫二: TFT LCD 產業之需求規劃 Demand Planning in TFT LCD Industry 計畫類別:整合型計畫 計畫編號: NSC 95 2213 E011 137 MY3 執行期限: 95 8 1 日至 98 7 31 主持人:王福琨 參與人員:林書全、吳仁均、黃志強 台灣科技大學工業管理系 Abstract In this study, a liquid crystal display (LCD) laptop shipment is investigated using a hierarchical forecasting (HF) comprised of three levels. In the past, there were three strategies concerning the HF, “top-down”, “middle-out” and “bottom-up”. Which of the three strategies works the best? In order to improve the performance of forecasting, we proposed a new approach for the forecasting model that considered the growth curve of the product in the market. The proposed forecasting methodology consists of four steps. First, three levels for the LCD laptop shipment is identified. Second, several forecasting techniques (transfer function, Bass model, Harvey model, Logistic model and Grey model) are used to forecast the future shipment at each hierarchical level. Third, various forecasting approaches and disaggregating proportion methods are adopted to obtain consistent forecasts at each hierarchical level. Finally, we made multiple comparisons from different forecasting approaches (top-down, middle-out and bottom-up) to find the best forecasting model for each hierarchical level. The results show that the best forecasting results of all levels can be improved. These results not only break through the standpoints of related HF studies in the past, but could also guide LCD manufacturers to adopt the best forecasting method. Key Words : Hierarchical forecasting, LCD laptop shipment, Transfer function, Bass model, Harvey model, Logistic model and Grey model INTRODUCTION Demand forecasting has been widely studied by researchers over the past decades. A critical issue is that choosing the appropriate level of aggregation depends on the decision-making process the forecast is expected to support. For example, in short term production planning, a very detailed demand forecast within the level of size and location is required. On the other hand, in the plant designing or budgeting, an aggregate forecast of the total market is needed. To provide the decision support information for many users, each representing different organizational functions and management echelons increases the reliance for family based forecasting. Hierarchical forecasting (HF) is a centralized system structured upon a process capable of satisfying varied information requirements (Fliedner and Mabert, 1992). HF is also important for its potential to improve forecast accuracy and to support improved decision-making. Over the past years several reports have appeared in the literature in support of HF. However, most papers were either focused on a new
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/27/2009 for the course IM MA420 taught by Professor Mar,lee during the Spring '09 term at National Taiwan University.

Page1 / 5

王福琨952221E011137MY3(第1年)

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online