近年來國內鋼鐵業者在經營上面臨極大挑戰，由於中國大陸鋼鐵廠以價格及產能優勢搶占大量市場，全球鋼鐵消費動能趨緩，世界各國環保法規要求嚴謹度提高及貿易保護的反傾銷策略，均影響到國內鋼鐵業者的銷售狀況，導致庫存產品大量堆積。
本研究目的在建立一個適用於傳統鋼鐵產業之庫存產品分類模式，從歷史訂單資料中找出對公司庫存產品有興趣的潛在客戶，應用決策樹分類技術找出庫存品與通銷品之間的關聯性，透過擁有高可解釋性的決策樹分類模式來對庫存產品做分類及預測可能購買庫存品的潛在客戶。
實際使用10個庫存品資料導入模型進行分類，決策樹模型分類的結果正確率在0.68到0.88之間，表示可以將該模型的分類結果提供給業務單位進行交叉行銷，讓業務人員在滿足客戶需求的前提下，採取主動出擊方式將庫存產品推薦給所需要之顧客，除可達到公司獲利、減少庫存持有成本之外，更可降低庫存水位之目標。

In recent years, the steel industry in Taiwan has faced major business challenges because the steel mills in China mainland have price and productivity advantages in global market. Slow global steel consumption, more stringent international environmental regulations, and trade protecting anti-dumping policies are the main factors that can affect the domestic steel industry’s sales and increase the accumulation in inventory. This study proposes an inventory classification method for traditional steel companies in Taiwan to find potential customers based on the historical data of orders for inventory products. The decision tree classification technique is applied to discover the associations between inventory and general products such that the induced decision trees can be helpful in identifying customers that could be interested in inventory products. Ten data sets for inventory products are summarized from historical ordering data to grow decision trees, and their resulting accuracies are all between 0.68 and 0.88. This suggests that the associations between inventory and general products represented in the decision trees can provide reliable information for the sales department to find potential customers of inventory products. Hence, the goals of increasing company profit and reducing inventory level and holding costs can be achieved.

中文
水戶誠一,(民國83年), 江先安 譯, 怎麼樣做好庫存管理, 方智出版社, 台北縣
片桐正,(民國90年), 庫存管理入門, 白惠齡譯, 小知堂文化事業有限公司, 台北市
周文賢,(民國88年), 行銷管理：市場分析與策略規劃, 智勝文化事業有限公司, 台北市
岡上友太郎、櫻井多賀司,(民國93年), 洪瑩珍 譯, 庫存管理實務入門, 博誌文化股份有限公司, 台北市
鹿野秀人、鬼澤康夫,(民國94年), 林利珉 譯, 庫存整頓實務圖解, 商周出版, 台北市
黃彥達,(民國92年), 庫存管理, 藍鯨出版有限公司, 台北市

英文
Bala, P. K. (2010). Decision tree based demand forecasts for improving inventory performance. Industrial Engineering and Engineering Management (IEEM), 2010 IEEE International Conference on.
Berry, M. J., & Linoff, G. (1997). Data mining techniques: for marketing, sales, and customer support: John Wiley & Sons, Inc.
Berry, M. J., & Linoff, G. S. (2004). Data mining techniques: for marketing, sales, and customer relationship management: John Wiley & Sons.
Braglia, M., Grassi, A., & Montanari, R. (2004). Multi-attribute classification method for spare parts inventory management. Journal of Quality in Maintenance Engineering, 10(1), 55-65.
Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and Regression Trees: CRC press.
Chai, J., Liu, J. N., & Xu, Z. (2013). A rule-based group decision model for warehouse evaluation under interval-valued Intuitionistic fuzzy environments. Expert Systems with Applications, 40(6), 1959-1970.
Gröger, C., Niedermann, F., & Mitschang, B. (2012). Data mining-driven manufacturing process optimization. Proceedings of the World Congress on Engineering.
Grossman, R. (2001). A top-ten list for data mining. SIAM News, 34(5), 1-2.
Hand, D. J., Mannila, H., & Smyth, P. (2001). Principles of Data Mining: MIT press.
Kass, G. V. (1980). An exploratory technique for investigating large quantities of categorical data. Applied statistics, 119-127.
Kendall, S. D. (2006). Customer service from the customer's perspective. Customer service delivery: Research and best practices, 3-21.
Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. International Joint Conference on Artificial Intelligence.
Partovi, F. Y., & Anandarajan, M. (2002). Classifying inventory using an artificial neural network approach. Computers & Industrial Engineering, 41(4), 389-404.
Quinlan, J. R. (1993). C4. 5: programs for machine learning (Vol. 1): Morgan kaufmann.
Raphel, M., & Raphel, N. (1995). Up the loyalty ladder: Turning sometime customers into full-time advocates of your business: HarperBusiness.
Rezaei, J., & Dowlatshahi, S. (2010). A rule-based multi-criteria approach to inventory classification. International Journal of Production Research, 48(23), 7107-7126.
Sheth, J. N., Mittal, B., & Newman, B. I. (1999). Customer behavior: consumer behavior and beyond: Dryden Press Fort Worth.
Sousa, I., & Wallace, D. (2006). Product classification to support approximate life-cycle assessment of design concepts. Technological Forecasting and Social Change, 73(3), 228-249.
Tomida, S., Hanai, T., Koma, N., Suzuki, Y., Kobayashi, T., & Honda, H. (2002). Artificial neural network predictive model for allergic disease using single nucleotide polymorphisms data. Journal of bioscience and bioengineering, 93(5), 470-478.
Wang, J., Zhu, W., Sun, D., & Lu, H. (2008). Application of SVM Combined with Mackov Chain for Inventory Prediction in Supply Chain. Wireless Communications, Networking and Mobile Computing
Witten, I. H., & Frank, E. & Mark, A.Hall (2011). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann,Burlington, Massachusetts
Yu, M.-C. (2011). Multi-criteria ABC Analysis using artificial-intelligence-based classification techniques. Expert Systems with Applications, 38(4), 3416-3421.