Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/19728
標題: 協同式銷售預測系統之研究
A Collaborative System for Sales Forecast
作者: 盧廷昌
Lu, Ting-Chang
關鍵字: SCM
供應鍊
Sales Forecasting
Forecast Accuracy
銷售預測
預測準確率
出版社: 資訊科學與工程學系所
引用: (一)、 中文部分 [11] 供應鏈之設計與管理/David Simchi-Levi, Philip Kaminsky, Edith Simchi-Levi McGraw-Hill著, 蘇雄義 譯, 譯自: Designing and Managing the Supply Chain: Concept, Strategies, and case studies, 2nd ed. [14]中華民國九十八年度年報以及九十九年股東常會議事手冊, 成霖企業股份有限公司 (二)、 西文部分 [1] Is smarter better? A comparison of adaptive, and simple moving average trading strategies Research in International Business and Finance, Volume 19, Issue 3, September 2005, Pages 399-411 [2] Makridakis et al., 1998 S. Makridakis, S. Wheelwright and R. Hyndman, Forecasting methods and applications (3rd ed.), John Wiley, New York (1998). [3] Makridakis et al., 1982 S. Makridakis, A. Andersen, R. Carbone, R. Fildes, M. Hibon and R. Lewandowski et al., The accuracy of extrapolation (time series) methods: Results of a previous termforecastingnext term competition, Journal of previous termForecastingnext term 1 (1982), pp. 111–153 [4] Billah B., King M.L., Snyder R.D., Koehler A.B. Exponential smoothing model selection for forecasting (2006) International Journal of Forecasting, 22 (2), pp. 239-247. [5] Brown, R. G. (1959). Statistical forecasting for inventory control. New York7 McGraw Hill. [6] Holt, C. C. (1957). Forecasting Trends and Seasonal by Exponentially Weighted Averages, ONR Memorandum No. 52, Carnegie Institute of Technology, Pittsburgh, USA (published in International Journal of Forecasting 2004, 20, 5–13). [7] Winters, P. R. (1960). Forecasting sales by exponentially weighted moving averages. Management Science, 6, 324–342. [8] Henderson, R., 1916. Note on graduation by adjusted average. Transactions of the Actuarial Society of America 17, 43 48. [9] Hyndman, R. J. and A. B. Koehler (2006) Another look at measures of forecast accuracy, International Journal of Forecasting, 22, 679-688. [13]Shiskin, J., Young, A.H., and Musgrave, J.C. (1967). The X-11 Variant of the Census Method II Seasonal Adjustment Program. Technical Paper 15, Bureau of the Census, U.S. Department of Commerce, Washington, D.C. [15] Hyndman, R. J., Koehler, A. B., Snyder, R. D., & Grose, S. (2002). A state space framework for automatic forecasting using exponential smoothing methods. International Journal of Forecasting,18, 439– 454. [16] Akaike, H. (1973). Information theory and an extension of the maximum likelihood principle. In B. N. Petrov, & F. Csaki (Eds.), Second international symposium on information theory (pp. 267– 281). Budapest7 Akademiai Kiado. [17] Snyder, R. D. (1985). Recursive estimation of dynamic linear statistical models. Journal of the Royal Statistical Society. Series B, 47, 272– 276. [18] Ord, J. K., Koehler, A. B., & Snyder, R. D. (1997). Estimation and prediction for a class of dynamic nonlinear statistical models. Journal of the American Statistical Association, 92,1621–1629. [19] E. S. Gardner, Jr., “Exponential smoothing: The state of the art – Part II,” International Journal of Forecasting, Vol. 22, No. 4 (October - December, 2006), pp. 637-666. 1999-On the asymmetry of the symmetric MAPE [10] Symmetric mean absolute percentage error, http://en.wikipedia.org/wiki/Symmetric_mean_absolute_percentage_error [12] Time Series Analysis: The Basics, Australian Bureau of Statistics http://www.abs.gov.au/websitedbs/d3310114.nsf/4a256353001af3ed4b2562bb00121564/b81ecff00cd36415ca256ce10017de2f!OpenDocument#WHAT%20IS%20SEASONALITY%3F
摘要: 在全球化激烈競爭的市場中,產品生命週期不斷縮短,供應商的選擇性不再侷限於國內,對於海外的供應商也會是考慮的範疇,在財務上,除了要積極的拓展業績開源之外,如何能夠壓低製造成本,配銷成本或者是庫存成本,也成為一家公司是否能夠持續獲利的關鍵因素。一項產品的製造,需要由供應端提供原物料,透過運輸並存放於公司的倉儲,由倉儲提取原料開始生產,成品最後被放入成品倉,等待訂單並且配送,配送有可能透過海運或空運到達客戶端,這些經過的點或設施,以及使用的運輸工具都是SCM (Supply Chain Management) 所需考慮的環節,每個點或設施通常與上下游的設施或運輸方式都有複雜的依存關係,我們稱呼這些由設施與彼此連結的複雜關係為物流網路(Logistics Network),物流網路包含供應商、倉庫、配銷中心、零售商以及流通在各設施中的原物料、再製品存貨、成品等,也就是從原料取得到生產最後配銷到零售商的流程,如何在每一個環節提升效率並且管控成本但是又不失產品的品質,是我們一再努力的。 成霖企業主要產品是衛浴設備,包含:水龍頭、臉盆、馬桶以及衛浴配件等,產品有成千上萬種,每一項產品的生產都需要向供應商下單以取得生產用料,那麼該下多少量,多久下一次,是否有經濟批量或者最小訂購量(MOQ, Minimum Order Quantity),是不是已經有在途的存貨,這些都是下單時所需考量的問題。為此,我們引進了Wolverine Inc.的DCM (Demand Chain Management) System,並且依據公司的需求,適度的客製演算法並且調整流程以符合公司所需,目前,已藉由此系統產出系統預測與下單量,文中會介紹我們開發團隊所使用的預測流程。然而,工具只是一種輔助工具,如何降低庫存成本,必須從過高的安全庫存量著手,而安全庫存量又與預測準確度息息相關,所以,提升預測準確率變成我們目前的首要之務。因此,我們需要有一套方法,不僅可以精確的計算銷售預測,同時也能夠檢討預測流程中各部門人員的預測準確率,以求整體提升我們的預測準確率,又能夠確保庫存水準是安全的。以下是我們團隊採用的產品銷售預測流程以及我們所提出的預測準確率的分析方法以及商業智慧(BI, Business Intelligent)平台在提升預測準確率的研究,目前已在本公司採用並且已經有顯著的改善。
In the competitive global market, the period of product life cycle is getting shorter and shorter. In order to reduce the overall product cost, suppliers needed to be deployed not only in-country but also around the globe. When it comes to supplier solicitation, we need to consider the transportation cost, procurement cost and inventory cost. We should be able to maximize the margin by taking all these cost factors into account. However, this is not an easy target to reach. When a good being produced, suppliers take the roles to provide raw material by truck, rail, sea or air to our warehouse, then we use these raw materials to make the parts or finished-goods. Some of the finished-goods will be distributed to customer or retailer's site, and rest of them will be stored in finished-goods warehouses. All the suppliers, factories, warehouses, distribution centers and sales channel are connected to each other. They are all the points that SCM should considered, and we call the facilities “logistics network”. All we have to do is to improve the service levels and control the costs between each node in the network. Globe Union Inc. is a company that produces faucet and bathroom product, when thousands of products are ordered or produced, the company needs to place purchase orders to the suppliers to get raw materials. Under the circumstances we should consider how many quantities should be ordered, how much lead time of the products will be produced and transferred to retailer or wholesaler channel, MOQ (Minimum Order Quantity) and lot-size are also the item attributes we should consider. We use DCM system and customized it to fulfill our purpose. For now it can help us to organize all the data and generate demand forecast and replenishment recommendations. Due to the long lead time between factories and distribution center (around 1 month to 3 months), we usually set higher safety stock level to prevent the inventory shortage in the past. However, in order to reduce the inventory cost we should lower the safety stock level. This will lead to the forecast accuracy of the inventory safety stocks. For this reason we proposed several methods to try to improve the forecast accuracy of active products and new products.
URI: http://hdl.handle.net/11455/19728
其他識別: U0005-2708201013553800
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-2708201013553800
Appears in Collections:資訊科學與工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館

Show full item record
 
TAIR Related Article
 
Citations:


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.