透過您的圖書館登入
IP:18.217.249.77
  • 學位論文

主權債券之信用違約轉換契約價格預測: 比較人工智慧模型的預測能力

The sovereign bond CDS prices prediction: The comparison of the ANN models

指導教授 : 陳若暉

摘要


本研究目的在比較人工智慧模型對於主權債券(Sovereign Bond)之信用違約轉換契約(Credit Default Swap,CDS)價格的預測能力,藉由七個投資人情緒指標(S&P500、恐慌指數、美元指數、倫敦銀行同業拆借利率、未平倉比率、商品研究局期貨價格指數與散戶投資人情緒指數)和五個人工智慧預測模型(隨機森林、支援向量機、決策樹、單純貝氏分類器、與K-近鄰演算法)來衡量。研究結果發現,隨機森林與決策樹模型有較高的預測能力,但在Diebold-Mariano (DM)檢定中,則是支援向量機、單純貝氏分類器、和決策樹為較佳的預測模型。本研究建議投資人,使用隨機森林與決策樹模型作為未來投資決策和風險管理的重要工具。再者,經濟蕭條期間,投資人亦可以用人工智慧預測模型,以預測信用違約轉換契約(CDS)並建構最佳避險策略。

並列摘要


This study is to compare which Artificial Neural Network (ANN) model has the best prediction to sovereign bond credit default swap (CDS). We use the seven sentiment indicators including the S&P500, VIX, USD index, LIBOR, Put/Call ratio, Commodity Research Bureau (CRB), and Association of Individual Investors (AAII). Five ANN forecast models were used such as the Random Forests (RF), Support vector machine (SVM), Decision tree, Naive Bayes Classifier (NBC), and K-Nearest Neighbor Algorithm (KNN). The result showed that the RF and Decision tree were the best prediction models for sovereign bond CDSs with higher accuracy and lower errors. Moreover, the DM test had the different results that SVM, NBC, and Decision tree were the best models. These findings suggest that investors can use RF and Decision models to make their future investment plan and minimize their investment risk. Furthermore, they can use ANN models to forecast the CDS to build the hedge strategy when facing the downturn economics cycle.

參考文獻


Al-Radaideh, Qasem A., Assaf, Adel Abu, and Alnagi, Eman (2013), Predicting Stock Prices Using Data Mining Techniques, The International Arab Conference on
Information Technology (2013’ACIT), 1-8.
Ang, Andrew, Gorovyy, Sergiy, and Van, Inwegen Gregory B. (2011), Hedge fund
leverage, Journal of Financial Economics, 102(1), 102-126.
Arora, Navneet, Gandhi, Priyank and Longstaff, Francis A. (2012), Counterparty credit risk and the credit default swap market, Journal of Financial Economics, 103(2), 280-293.

延伸閱讀