倒傳遞類神經網路於薄膜濺鍍製程材料下銷售預測之的研究.docVIP

倒傳遞類神經網路於薄膜濺鍍製程材料下銷售預測之研究 藍天雄1 陳品璋2 藍俊雄3 莊凱棋4 1育達商業科技大學資訊管理系 2育達商業科技大學資訊管理系 3醒吾技術學院企業管理系 4育達商業科技大學資訊管理系 摘要 企業經營管理最重要的ㄧ環是銷售預測。因此，提高預測準確性為首要追求目標之ㄧ。本研究以光電材料—靶材產業為例，選定一間公司為個案樣本，以2004-2011年個案公司所提供的歷史銷售記錄，藉由倒傳遞類神經網路所具有高速計算能力、、學習及容錯能力等優點12個神經元、隱藏層8個神經元、輸出層1個神經元，參數則設定為學習循環次數20000次、學習速率0.1，可獲得最佳之訓練值。 本研究之結果顯示，採用倒傳遞類神經網路學習的訓練值，與實際的銷售值相當接近，其關聯性和模式配適度分別高達99.91％過度造成存貨成本，降低缺貨所造成之訂單流失等問題。關鍵字：Forecasting on the Thin Film Sputtering Process Material Using Back Propagation Network 1Tian-Syung Lan, 2 Pin-Chang Chen, 3Chun-Hsiung Lan, 4Kai-Chi Chuang 1Department of Information Management, Yu Da University, (tslan@ydu.edu.tw) 2Department of Information Management, Yu Da University, (chenpc@ydu.edu.tw) 3Department of Business Administration, Hsing Wu Institute of Technology, (100001@mail.hwc.edu.tw) 4Department of Information Management, Yu Da University, ydu.edu.tw) ABSTRACT Sales forecasting is the most important aspect in managing company operations. The forecast accuracy becomes an important goal for companies. This study introduces the target industry (an optoelectronic material) as an example for case study which the annual sales amounts from year 2004 to year 2011 are provided by the company. By using the back propagation neural network with the advantages of high-speed computing power, fast recall speed, high learning accuracy, and fault tolerance, the neural network uses 12 neurons in the input layer, 8 neurons in the hidden layer, and 1 neuron in the output layer. Through a learning cycle of 20,000 times and a learning rate of 0.1, the forecast values after conducting training and testing are received. It is shown that the forecasted output values by the back propagation neural network are extremely related to the actual sales values. Additionally, the correlation and the R-squared values are 99.91% and 0.996, respectively. It indicates that the future case company’s chromium target sales can be satisfactorily forecasted