臺灣博碩士論文加值系統

隨著金融業的競爭環境日趨嚴峻，本研究主要目的乃透過集成學習技術建立有效之信用貸款購買行為之預測模型，期許可幫助業者利用既有客戶資料，拓展更廣泛的信用貸款業務。

集成學習是指藉由多種模型建構工具，使其相互結合來建立模型，廣泛運用於分類問題上。透過整體方法降低學習演算法的偏差及變異，與單一模型相比較，集成學習可增加模型的穩健性與準確率。本研究運用集成學習方法中的多數投票概念，建立信貸客戶購買行為之預測模型。

以某金融機構電話行銷信貸客戶資料為研究範例，本研究使用15個變數作為輸入變項，預測信用貸款成交與否情形。主要分為兩個階段：第一階段分別利用羅吉斯迴歸(Logistic Regression)、鑑別分析(Discriminant Aanlysis)、支援向量機(SVM)、極限學習機(ELM)及倒傳遞類神經網路(BPN)等五種機器學習方法建構五種不同的信貸客戶分類模型，預測電話行銷之客戶是否購買信貸產品。第二階段將五種分類模型進行多數投票，以建構穩健之信貸客戶購買行為之預測模型。

研究結果顯示，在整體鑑別率、kappa值、最小期望誤置成本、型二誤差機率與F_1 指標等五項指標綜合衡量下，運用集成學習概念之分類效果較單一分類模型佳。

In financial industry, the environment is getting much harsher than ever before. To be outstanding in financial sector, bankers have been tried to satisfy the need of customers as they can whether in service quality or in service area. Considering the characteristics of the consumer credit loans which are less risky and thriving, bankers are keen to sell consumer credit loans. The objective of the proposed study is to explore the performance of classification model for classifying fiduciary purchasing behavior using ensemble learning techniques. This study proposed a hybrid Logistic regression, Discriminant analysis, Extreme learning machine, Support vector machine and Artificial neural networks method to upgrade the performance of classification model comparing to single learner above.
To demonstrate the effectiveness of the ensemble learning approach, classification tasks are performed on one consumer dataset of credit loans telemarketing. 15 variables are adopted in this study. The result shows that the proposed approach is better than other five single classification models.

目錄
第壹章 1
第壹章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 3
第三節 研究流程 4
第貳章 文獻探討 5
第一節 信用貸款 5
第二節 分類模型建構工具 7
第三節 信用貸款模型 14
第參章 研究方法 16
第一節 研究架構 16
第二節 羅吉斯迴歸 18
第三節 鑑別分析 20
第四節 支援向量機 21
第五節 倒傳遞類神經網路 23
第六節 極限學習機 24
第七節 集成學習 26
第肆章 實證研究 28
第一節 實驗說明 28
第二節 模式建構 30
第三節 綜合比較 44
第四節 重要變數之討論 49
第伍章 結論與建議 50
第一節 研究結論 50
第二節 後續建議 52

表目錄
表 2-1-1 業者信貸商品比較表 6
表 4-1 1 樣本資料分布情形表 28
表 4-1-2 變數定義表 29
表 4-2-1 組測試樣本資料分佈情形表 30
表 4-2-2 羅吉斯迴歸方程式(Fold 1)(續後頁) 32
表 4-2-3 羅吉斯迴歸分析實證結果( Fold 1 ) 33
表 4-2-4 羅吉斯迴歸分析交叉驗證總表 34
表 4-2-5 分類函數係數表(Fold 1) 34
表 4-2-6 鑑別分析實證結果(Fold 1) 35
表 4-2-7 鑑別分析交叉驗證總表 35
表 4-2-8 最佳參數組合搜尋表(Fold 1) 37
表 4-2-9 SVM實證結果(Fold 1) 38
表 4-2-10支援向量機交叉驗證總表 38
表 4-2-11BPN於不同參數設定之結果表(Fold 1)(續後頁) 39
表 4-2-11BPN於不同參數設定之結果表(Fold 1)(接前頁) 40
表 4-2-12BPN實證結果(Fold 1) 40
表 4-2-13BPN交叉驗證總表 41
表 4-2-14ELM 實證結果(Fold 1) 42
表 4-2-15ELM交叉驗證總表 42
表 4-2-16集成實證結果(Fold 1) 43
表 4-2-17集成學習交叉驗證總表 43
表 4-3-1 交叉驗證鑑別結果-正確鑑別率表 43
表 4-3-2 交叉驗證鑑別結果-kappa statistic表 45
表 4-3-3 交叉驗證鑑別結果-期望誤置成本表 46
表 4-3-4 各模型發生型一與型二誤差之機率表 47
表 4-3-5 交叉驗證鑑別結果- F1表 48
表 4-5-1 綜合比較表 49

圖目錄
圖 1-3-1 研究流程圖 4
圖 3-1-1 研究架構圖 17
圖 3-2-1 羅吉斯迴歸之S型函數模型圖 19
圖 3-5-1 倒傳遞類神經網路網路架構圖 23

中文部分
1.王智弘(2002)。應用資料探勘技術分析及預測銀行顧客貢獻度之研究。國立中正大學資訊工程研究所未出版碩士論文，嘉義縣。
2.王濟川、郭志剛(2003)。Logistic 迴歸模型-方法及應用。台北市：五南圖書出版股份有限公司。
3.李宜致(2008)。資料探勘手術後減重效果分類模式之建構。輔仁大學商學研究所未出版博士論文，新北市。
4.林盟凱(2004)。信用評等時間序列資料分析-結合效能提升技術之類神經網路分類模型。世新大學資訊管理學系未出版碩士論文，台北市。
5.林蔚蒲(2013)。復健前後的中風病人各項量表的比較分析。國立中山大學機械與機電工程學系研究所未出版碩士論文，高雄市。
6.張慶光(2006)。以資料探勘之決策樹方法建立小額信貸評分模型研究。國立台灣大學商學組未出版碩士論文，台北市。
7.陳怡妃(2003)。資料探勘顧客保留分類模式之建構-以健康休閒俱樂部為例。天主教輔仁大學管理學研究所未出版碩士論文，新北市。
8.陳順宇(2004)。多變數分析( 3版)。台北市：華泰文化事業股份有限公司。
9.彭慧雯(2001)。建構信用卡資料挖礦架構及其實證研究。國立台北科技大學生產系統工程與管理研究所未出版碩士論文，台北市。
10.温堯欽(2013)。網路入侵與攻擊偵測之實作研究-使用最佳專機分類法。國立聯合大學資訊管理學系碩士班未出版碩士論文，苗栗縣。
11.趙李英記(1999)。運用集成學習分類於白血病腫瘤基因之研究。中國文化大學資訊管理學系未出版碩士論文，新北市。
12.劉書汎(2009)。信用卡違約風險評估模型-應用粗糙集與因素分析。朝陽科技大學財務金融系碩士班未出版碩士論文，台中市。
13.蔡佩芬(2012)。以兩種資料探勘方式預測透析中低血壓事件:比較支援向量機與羅吉斯迴歸法。中臺科技大學健康產業管理研究所未出版碩士論文，台中市。
14.蔡博安(2012)。應用支援向量機與集成學習法預測工程專案績效。國立高雄應用科技大學土木工程與防災科技研究所未出版碩士論文，高雄市。
15.謝弘一(2011)。資料探勘於信用卡顧客行為評分模型之建構。天主教輔仁大學商學研究所未出版博士論文，新北市。
16.謝邦昌(2006) 。資料採礦與商業智慧。台北市：鼎茂圖書出版股份有限公司。

網路部份
1.中時電子報(2013)，取自於
http://money.chinatimes.com/news/news-content.aspx?id=20131108000043&cid=1210



英文部分
1.Akgun, A. (2012). A comparison of landslide susceptibility maps produced by logistic regression, multi-criteria decision, and likelihood ratio methods: a case study at İzmir, Turkey. Landslides, 9(1), 93-106.
2.Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. Journal of Finance, 23(4), 589-609.
3.Berkson, J. (1944). Application of the Logistic function to bioassay. Journal of the American Statistical Association, 37, 357-365.
4.Chen, F. L.,& Ou, T. Y. (2011). Sales forecasting system based on Gray extreme learning machine with Taguchi method in retail industry. Expert systems with Applications, 38(3), 1336-1345.
5.Chen, W. H., & Shih, J. Y. (2006). A study of Taiwan’s issuer credit rating systems using support vector machines. Expert Systems with Applications, 30(3), 427-435.
6.Clayton, G. E., & Cate, T. (2004). Predicting MBA no-shows and graduation success with discriminant analysis. International Advances in Economic Research, 10(3), 235-243.
7.Crook, J. N., Edelman, D. B., & Thomas, L. C. (2007). Recent developments in consumer credit risk assessment. European Journal of Operational Research, 183, 1447-1465.
8.Dietterich, T. G. (Ed.). (2000). Ensemble methods in machine learning. NY: Springer.
9.Fisher, R. A. (1938). The statistical utilization of multiple measurements. Annals of Eugenics, 8, 376-386.
10.Hagan, M. T., Demuth, H. B., & Beale, M. H. (1996). Neural network design. Boston: Pws.
11.Hansen, L. K., & Salamon, P. (1990). Neural network ensembles. IEEE transactions on pattern analysis and machine intelligence, 12, 993-1001.
12.Hosmer, D. W., & Lemeshow, S. (1989). Applied logistic regression. NY: John Wiley & Sons, Inc.
13.Hsieh, N. C., & Huang, L. P. (2010). A data driven ensemble classifier for credit scoring analysis. Expert Systems with Applications, 28(4), 655-665.
14.Huang, C. L., Chen, M. C., & Wang, C. J. (2007). Credit scoring with a data mining approach based on support vector machines. Expert systems with Applications, 33(4), 847-856.
15.Huang, G. B., Ding, X. J., & Zhou, H. M. (2010). Optimization method based extreme learning machine for classification. Neurocomputing, 74(1-3), 144-163.
16.Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: theory and applications, Neurocomputing, 70(1-3), 489-501.
17.Huang, Z., Chen, H., Hsu, C. J., Chen, W.-H., & Wu, S. (2004). Credit rating analysis with support vector machines and neural networks: A market comparative study. Decision Support Systems, 37(4), 543-558.
18.Hus, C.-W., Chang, C.-C., & Lin, C.-J. (Eds.). (2003). A practical guide to support vector classification. Taipei: National Taiwan University.
19.Johnson, R. A., & Wichern, D. W. (Eds.). (1992). Applied multivariate statistical analysis. NJ: Prentice-Hall.
20.Karra, A., & Krichene, A. (2012). Credit–Risk Assessment Using Support Vectors Machine and Multilayer Neural Network Models: A Comparative Study Case of a Tunisian Bank. Journal of Accounting and Management Information Systems, 11(4), 587-620.
21.Landis, J., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(Mar.), 159-174.
22.Lee, G., Sung, T. K., & Chang, N. (1999). Dynamics of modeling in data mining: Interpretive approach to bankruptcy prediction. Journal of Management Information Systems, 16(1), 63-85.
23.Lee, H., Jo, H., & Han, I. (1997). Bankruptcy prediction using case-based reasoning, neural networks, and discriminant analysis. Expert Systems with Applications, 13(2), 97-108.
24.Li, S.-T., Shiue, W., & Huang, M.-H. (2006). The evaluation of consumer loans using support vector machines. Expert Systems with Applications, 30(4), 772-782.
25.Luo, S.-T., Cheng, B.-W., & Hsieh, C.-H.(2009). Prediction model building with clustering-launched classification and support vector machines in credit scoring. Expert Systems with Applications, 36(4), 7562-7566.
26.McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4), 115-133.
27.Mileris, R. (2010). Estimation of loan applicants default probability applying discriminant analysis and simple Bayesian classifier. Economics & Management, 15, 1078-1084.
28.Nagadevara, V. (2010). Hybrid models and error weighting for prediction customer churn in telecom industry. Review of Business Research, 10(1), 35-45.
29.Odum, E. P. (1971). Fundamental of ecology. Phidadelphia: W. B. Saunders Co.
30.Osmar, R. Z. (1999). Resource and knowledge discovery from the Internet and multimedia repositories. Unpublished doctoral dissertation, Simon Fraser University, Canada.
31.Polikar, R. (2006). Ensemble based systems in decision making. Circuits and Systems Magazine, IEEE, 6(3), 21- 45.
32.Schölkopf, B., & Smola A. J. (2002). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MA: MIT Press.
33.Shin, K.-S., Lee, T.S., & Kim, H.-j (2005). An Application of Support Vector Machines in Bankruptcy Prediction Model, Expert Systems with Applications, 28, 127-135.
34.Upadhyay, A., Bandyopadhyay, G., & Dutta, A. (2012). Forecasting Stock Performance in Indian Market using Multinomial Logistic Regression. Journal of Business Studies Quarterly, 3(3), 135-149.
35.Vapnik, V. N. (Ed.). (2000). The Nature of Statistical Learning Theory. New York: Springer.
36.Vapnik, V., Golowich, S. E., & Smola, A. (1997). Support vector method for function approximation, regression estimation, and signal processing. Advances in neural information processing systems, 281-287.
37.Verhulst, P. E. (1838). Notice sur la loi que la population suit dans son accroissement. Correspondence Mathematique et. Physique, 10, 113-121.
38.Wang, G., Hao, J., Ma, J., & Jiang, H. (2011). A comparative assessment of ensemble learning for credit scoring. Expert systems with applications, 38(1), 223-230.
39.Wang, Y. G., Cao, F. L., & Yuan, Y. B. (2011). A study on effectiveness of extreme learning machine. Neurocomputing, 74(16), 2483-2490.
40.West, D. (2000). Neural network credit scoring models. Computers and Operations Research, 27(11-12), 131-1152.
41.Windeatt, T., & Ardeshir, G. (2004). Decision tree simplification for classifier ensembles. International Journal of Pattern Recognition and Artificial Intelligence, 18(05), 749-776.
42.Yu, L., Yue, W., Wang, S., & Lai, K. K. (2010). Support vector machine based multiagent ensemble learning for credit risk evaluation. Expert Systems with Applications, 37(2), 1351-1360.
43.Yuan, Y. B., Wang, Y. G., & Cao, F. L. (2011). Optimization approximation solution for regression problem based on extreme learning machine. Neurocomputing, 74(16), 2475-2482.
44.Zhang, G., Patuwo, B. E., & Hu, M. Y. (1998). Forecasting with artificial neural networks: The state of the Art. International Journal of Forecasting, 14, 35-62.
45.Zoratti, S., & Gallagher, L. (2013). Precision Marketing-Minimizing revenue through relevance. Taipei: Kogan Page Ltd.