Demand Prediction Strategy In A Hybrid MTO/MTS Production Environment

• Main Authors: Shih-FengLin, 林世峰
• Other Authors: Chin-Ho Lin
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/68978888201629577375

碩士 === 國立成功大學 === 工業與資訊管理學系碩士在職專班 === 103 === The purpose of this study is to establish an inventory management system suitable for the special alloy steel industry which meets existing requirements while maintaining the inventory of semi-finished products at the lowest possible level. Therefore, this study utilized methods of moving average, weighted moving average, exponential smoothing, and least squares to predict customer demand and, using comparison, determine which method also offers the lowest level of inventory. The expected results were adjusted based on parameters selected with the help of interviews with specialists, in the hope that the system meets customer demand and provides a reference for semi-finished product management strategies in the future. The results showed that the prediction method most suitable for the subject industry was the weighted moving average method, which yielded prediction values that were closer to actual customer demand and was able to effectively decrease the amount of semi-finished products in the inventory - more effectively than the inventory management method previously deployed by the subject company. Also, analysis showed that the opinions from specialists had a certain level of influence. Therefore, when conducting demand prediction, specialist opinions must be taken into consideration.