政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/119884

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/119884

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | Items with full text/Total items : 113318/144297 (79%)
Visitors : 50951885 Online Users : 952

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

Scope

please add "double quotation mark" for query phrases to get precise results

please goto advance search for comprehansive author search

Adv. Search

Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer

Goto mobile version

政大典藏 > College of Commerce > Department of Money and Banking > Theses > Item 140.119/119884

Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/119884

Title:	擔保房貸憑證(CMOs)之評價：應用類神經網路預測提前還款率 Pricing Collateralized Mortgage Obligations: Using Neural Network to Forecast Prepayment Rate
Authors:	張憲明 Chang, Hsien-Ming
Contributors:	林士貴陳亭甫 Lin, Shih-Kuei Chen, Ting-Fu 張憲明 Chang, Hsien-Ming
Keywords:	房屋抵押貸款證券化擔保房貸憑證(CMOs) 提前還款類神經網路對數常態遠期利率(Lognormal Forward LIBOR Model, LFM)市場模型 Mortgage securities Collateralized mortgage obligations (CMOs) Prepayment Neural network Lognormal forward LIBOR model
Date:	2018
Issue Date:	2018-09-03 15:48:23 (UTC+8)
Abstract:	本研究主要透過使用類神經網路的方法來預測擔保房貸憑證(CMOs)之提前還款風險並加以評價，並且與另外兩種模型進行比較，PSA/CPR模型和美國官方(Office Thrift Supervision; OTS)30年期固定利率住宅抵押貸款動態提前清償模型，其中PSA/CPR模型為靜態模型，OTS模型為動態模型，另外由於實證個案現金流與LIBOR利率有關，因此採用的利率模型為對數常態遠期利率(Lognormal Forward LIBOR Model, LFM)市場模型，且因為擔保房貸憑證(CMOs)涉及提前還款風險以及眾多風險，並無法找出封閉解，因此採用蒙地卡羅模擬法來作為評價模型。透過蒐集Fannie Mae公開的房屋抵押貸款資料來做實證，實證結果有以下貢獻，第一，類神經網路預測提前還款率均方誤差(MSE)小於PSA/CPR模型的均方誤差，所以類神經網路在預測提前還款率的方面優於PSA/CPR模型。第二類神經網路模型得出個案的發行機構低估發行當下所設定之提前還款率，而動態模型的OTS模型也得到相同結果，綜合以上兩點，得到類神經網路模型預測提前還款率的評價結果比PSA/CPR模型更接近真實價格。 This paper used the Neural Network to forecast the prepayment rate of Collateralized Mortgage Obligations (CMOs), and then pricing it. Comparing the Neural Network Model with other prepayment model: PSA/CPR (static) Model and Office Thrift Supervision Model. Because the empirical analysis of this paper is related to LIBOR, we use LFM to simulate then LIBOR. CMOs involves a lot of risk like prepayment risk, so there is no close form of CMOs’ price, and we use Monte Carlo Method to pricing. The data for Neural Network is from Fannie Mae. There are some conclusions as following. First, the MSE of Neural Network is lower than MSE of the PSA or CPR model. Second, the prepayment rate of Neural Network is higher than the prepayment rate of PSA or CPR model, and the prepayment rate of OTS model is higher than the prepayment rate of PSA or CPR model. Finally, the price of Neural Network is closer to the real value than the price of the PSA or CPR model.
Reference:	中文文獻 [1] 王琮生 (2003)，「房貸保險之費率結構分析-競爭風險模型之應用」，朝陽科技大學財務金融系碩士班碩士論文。 [2] 何澤蘭 (1999)，「台灣不動產抵押債券證券化之推行及評價」，碩士論文，國立台灣大學財務金融研究所碩士論文。 [3] 李俊民 (2006)，「不動產抵押貸款證券化之評價─以中國信託商業銀行特殊目的信託抵押貸款受益證券為例」，世新大學財務金融研究所碩士論文。 [4] 林宗漢 (2003)，「應用存活分析於不動產抵押債權證券評價之研究」，朝陽科技大學財務金融系碩士班碩士論文。 [5] 高心怡 (2000)，「結合Hull-White 利率模型與PHM 提前清償模型評價CMO 利率衍生性商品」，國立台灣大學財務金融研究所碩士論文。 [6] 張繼文 (2010)，「擔保房貸憑證 (CMOs) 評價---以BGM利率模型為例」政治大學金融研究所學位論文 [7] 黃玉霜, 周清佳, & 林哲群 (2003)，「應用動態提前清償模型評價住宅抵押貸款證券」住宅學報, 中華民國住宅學會, 12(1), 43-56. [8] 黃世富 (2006)，「考慮違約損失下CMO商品的風險溢酬－應用One Factor Gaussian Copula 模型」，國立中正大學財務金融研究所碩士論文。英文文獻 [1] Ambrose, B. W. and Michael, L. (2001), “Prepayment Risk in Adjustable Rate Mortgages Subject to Initial Year Discounts: Some New Evidence,” Real Estate Economics, Vol. 29, No. 2, pp.305-327. [2] Dunn, K. B. and McConnell, J. J. (1981), “A Compare of Alternative Models for Pricing GNMA Mortgage-Back Securities,” Journal of Finance Vol.36, pp.471-484. [3] Dunn, K. B. and McConnell, J. J. (1981), “Valuation of GNMA Mortgage-Backed Securities,” Journal of Finance, Vol.36, pp.599-616. [4] Deng, Y. H., Quigley, J. M. and Van Order, R. (1996), “Mortgage Default and Low Down Payment Loans: The Costs of Public Subsidy,” Regional Science and Urban Economics, Vol. 26, pp.263-285. [5] Deng, Y. H. (1997), “Mortgage Termination: An Empirical Hazard Model with Stochastic Term Structure,” Journal of Real Estate Finance and Economics, Vol.14, pp.309-331. [6] Green, J. and Shoven, J. (1986), “The Effects of Interest Rates on Mortgage Prepayments,” Journal of Money, Credit, and Banking, Vol.18, pp.41-59. [7] Kau, J. B., Keenan, D. C., Muller, W. J. Ⅲ and Epperson, J. F. (1993), “Option Theory and Floating-Rate Securities with a Comparison of Adjustable- and Fixed-Rate Mortgages,” Journal of Business, Vol. 66, No.4, pp.595-618. [8] Kau, J. B., Hilliard, J. E. and Slawson, V. C. (1998), “Valuing Prepayment and Default in a Fixed-Rate Mortgage: A Binomial Options Pricing Technology,” Real Estate Economics, Vol. 26, No.3, pp.431-468. [9] Riksen, R., Spreij, P. J. C. and den Iseger, P. W. (2017), “Using Artificial Neural Networks in the Calculation of Mortgage Prepayment Risk.” [10] Schwartz, E. S. and Torous, W. N. (1989), “Prepayment and the Valuation of Mortgage-Backed Securities,” Journal of Finance 44, 375 - 392. [11] Waller, B. and Aiken, M. (1998), “Predicting Prepayment of Residential Mortgages: a Neural Network Approach,” International Journal of Information and Management Sciences, 9, 37-44.
Description:	碩士國立政治大學金融學系 105352032
Source URI:	http://thesis.lib.nccu.edu.tw/record/#G0105352032
Data Type:	thesis
DOI:	10.6814/THE.NCCU.MB.029.2018.F06
Appears in Collections:	[Department of Money and Banking] Theses

Files in This Item:

File	Size	Format
203201.pdf	2353Kb	Adobe PDF2	13	View/Open

All items in 政大典藏 are protected by copyright, with all rights reserved.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - Feedback