國立臺灣大學工業工程學研究所Chen, ArgonArgonChenGuo, Ruey-ShanRuey-ShanGuoChang, Shi-ChungShi-ChungChangHuang, TonnyTonnyHuangYang, KyleKyleYangTzeng, JanetJanetTzeng2006-09-272018-06-292006-09-272018-06-292003http://ntur.lib.ntu.edu.tw//handle/246246/200609271216533676342003 deliverable report:. forecasting methodologies for multidimensional aggregated demands. task 879.001: intelligent demand aggregation & forecast solutions. project 879: demand data mining & planning in semiconductorIn 2002, to cope with demand uncertainty, we have defined and proposed optimum demand planning hierarchy (DPH) to best support different granularities of planning activities. (see 2002 deliverable report). This year, the proposed DPH is extended from one-product DPH to hierarchical-product DPH. In addition, the DPH concept has been realized in a software system prototype, referred to as DPH Planner. In the DPH planner, the optimum DPH with the least demand fluctuation can be automatically created. Moreover, users can define their current demand planning practice in the DPH planner. With the benchmark of the optimum DPH, a what-if interface is also provided to allow users adjust their DP practice.application/001.pdf365472 bytesapplication/pdfzh-TWconference paperhttp://ntur.lib.ntu.edu.tw/bitstream/246246/20060927121653367634/1/2003 deliverable report 879.001.pdf