應用挖掘模糊規則建立新產品發展決策系統

Building New Product Decision Support System by Using Mining Fuzzy Rules

蔡源成(Yuan-Cheng Tsai) ； 李淑芳(Su-Fang Lee) ； 紀文章(Wen-Jang (Kenny) Jih)

《資訊管理學報》 13卷2期 (2006/04) Pp. 279-309

https://doi.org/10.6382/JIM.200604.0279

摘要

近年來，由於大型資料庫與資料倉儲迅速增加，從龐大資訊中挖掘有效資訊與知識成為重要的研究議題。尤其企業在資源限制環境下，面對新產品開發設計過程中，常因不明確的市場需求，而無法決定新產品的規格，導致產品研發與上市的時間延遲。因此，如何應用快速發展的資訊技術，結合龐大的資料庫，建立有效企業新產品發展輔助決策系統成為產品發展管理的熱門議題。本研究提出應用模糊理論描述問題相關屬性與應用類神經演算法，建立『啟發式模糊類神經演算法』(HFNNA)，搜尋潛藏在資料庫中有效的相似性規則，並經由有效的規則輔助企業，在面對不確定的市場環境下，新產品開發設計初期決定產品規格。本研究期望經由HFNNA，可達到以下幾點目的：(1)有效改善傳統的類神經系統的的架構與真實性問題間的差距。(2)建立有效的模糊規則系統。(3)應用擷取出的模糊規則建立決策輔助系統，並有效輔助企業面對不確定的市場環境。(4)除了搜尋龐大資料內蘊藏的規則之外，本研究並期望經由HFNNA，更有效率輔助企業明確了解龐大資料下蘊藏的潛藏知識。

關鍵字

產品發展管理 ； 模糊類神經 ； 資料挖掘 ； 決策輔助系統

並列摘要

In Recent years, due to the increasing use of very large databases and data warehouses, mining useful information and helpful knowledge from transaction is evolving into an important research area. The object of this paper is support business quick to determine the specification of new product in an uncertain environment by using data mining technology. The paper has been build the 'Heuristic Fuzzy Neural Network Algorithm' (HFNNA) based on Fuzzy Neural Network and the idea of to class with product's attribute. The result of this paper is proved that (1) the proposed algorithm is improved difference between neural network and real problem, (2) the proposed algorithm is built the effective data mining system, (3) using Fuzzy Association Rules inducted by the proposed algorithm are build decision support system and support business to make decision in an uncertain environment and (4) searching and collecting the effect knowledge hold on large databases and data warehouses.

並列關鍵字

product development management ； fuzzy neural network ； data mining ； decision support system

參考文獻

Agile Software(2000).White paper, Agile Software Company.

Benitez, J. M.,Castro, J. L.,Requena, I.(1997).Are artificial neural network black boxes.IEEE Transaction on Neural Network.8(5),1156-1164.

Chen, Z.(2001).Data Mining and Uncertain Reasoning: An Integrated Approach.John Wiley & Sons.

Dubois, D.,Prade, H.(1988).Possibility Theory: An Approach to Computerized Processing of Uncertainty.New York:Plenum Press.

Hong, T. P.,Lin, K. Y.,Wang, S. L.(2003).Fuzzy data mining for interesting generalized association rules.Fuzzy Sets and Systems.138,255-269.