透過您的圖書館登入
IP:18.221.165.246
  • 期刊

GA-SVM組合式信用風險財務危機模型之研究

An Integrated GA-SVM Approach for Credit Risk Prediction: An Example for Savings and Loan Association

若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


金融機構客戶的信用風險預測一直是很重要的議題,其與金融機構決策與獲利息息相關,至今已有許多預測模型被應用於信用風險預測,包括最近提出的Support Vector Machine(SVM)演算法,而SVM方法亦被拿來與Neural Network(NN)、Logistic Regression(LR)比較,顯示有較佳的結果。Genetic Algorithm(GA)演算法長久以來搭配其他預測技術如:NN,但GA與SVM結合在一起的相關研究並不多見,特別在於信用風險預測。本研究之目的在發展一套GA-SVM的預測方法,使用subset selection及parameter optimization,以基層金融機構客戶破產預測為例,並與一般常用的金融機構放款客戶破產預測方法做一比較。

並列摘要


Credit risk prediction is an important and widely studied topic since it has significant impact on financial institution lending decision and profitability. There have been many predication models applied to this area, including the recently proposed Support Vector Machine (SVM). The SVM-based method has been compared with other methods, such as neural network (NN) and logistic regression, and shown better results. For a long time, genetic algorithm (GA) has been applied in conjunction with other prediction techniques such as NN. However, few studies have dealt with the integration of GA and SVM, especially on credit risk prediction. The study proposes a method of improving SVM performance from subset selection and parameter optimization by combining the GA technique. Using the sample data for savings and loan association, the prediction power of the proposed GA-SVM approach is compared with other methods on customer bankruptcy prediction.

參考文獻


歐仁和(2002)。信用合作社行銷策略分析。信用合作季刊。71,16-30。
Agrawal, R.,K. Deb(1995).Simulated Binary Crossover for Continuous Search Space.Complex Systems.9,115-148.
Altman, E. I.(1968).Financial Ratios, Discriminant Analysis and Prediction of Corporate Bankruptcy.Journal of Finance.23,589-609.
Beaver, W.(1996).Financial Ratios as Predictos of Failures, in Empirical Research in Accounting.Journal of Accounting Research (Supplement).4,71-102.
Blum, M.(1974).Failing Company Discriminant Analysis.Journal of Accounting Research.12,1-25.

延伸閱讀