政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/118238

政大典藏 > College of Commerce > Department of Money and Banking > Theses > Item 140.119/118238

Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/118238

Title:	市場因子於倒傳遞類神經網路對信用評等之影響 The Effect of Market Factor in the Back Propagation Neural Network on Credit Rating
Authors:	饒宇軒 Jao, Yu-Hsuan
Contributors:	廖四郎 Liao, Szu-Lang 饒宇軒 Jao, Yu-Hsuan
Keywords:	倒傳遞類神經網路模型信用評等 KMV模型違約距離 Back propagation neural network model Credit rating KMV model Distance to default
Date:	2018
Issue Date:	2018-07-03 17:26:28 (UTC+8)
Abstract:	在2007年的金融危機後，外部評等機構信用評等的可信度受到打擊，外部信用評等機構的信用評等無法反映公司的經營能力。而BASEL II協定中，允許銀行經過主管機關核准後，使用內部模型法評估自身的信用風險。在這樣的條件下，銀行為了加強對自身信用風險的控管，我認為銀行將會開始發展自己內部的信用評等模型。本研究將變數分為財務變數和市場變數，財務變數是根據資產管理能力、獲利能力、財務結構和償債能力這四項因素，選取15項財務指標；市場變數為該公司的股票波動度和違約距離(Distance to Default, DD)作為市場變數。研究樣本為2000年到2008年半導體公司每季的信用評等將其分為三類，使用倒傳遞類神經網路模型進行分析。本研究中有模型A和模型B，模型A為只使用財務變數的倒傳遞類神經網路，模型B為使用財務變數和市場變數的倒傳遞類神經網路，並比較兩個模型的預測準確度。經由實證結果發現加入違約距離後，信用評等為第三類的資料能夠被有效的預測到，這是只使用財務比率為變數的倒傳遞類神經網路所無法辦到的。加入違約距離後，同時也使得整體準確度也由55.56%提升為58.89%。 In the financial crisis of 2007, the credibility of external rating agencies was undermined and the credit ratings of external credit rating agencies could not reflect the company`s operating capabilities. In the BASEL II agreement, banks are allowed to pass the approval of the competent authority and use the internal model method to assess their own credit risk. Under such conditions, in order to strengthen the bank`s control over its own credit risk, I think banks will begin to develop their own internal credit rating models. This study divides the variables into financial variables and market variables. The financial variables are based on four factors, asset management capabilities, profitability, financial structure and solvency. In the study, 15 financial indicators are selected as a financial variable. Market variables are the company`s stock volatility and Distance to Default (DD) as a market variable. The sample for the study was divided into three categories for each quarter of the credit rating of semiconductor companies from 2000 to 2008, and was analyzed using back propagation neural network model. In this study, there are Model A and Model B. Model A is a back propagation neural network that only uses financial variables. Model B is a back propagation neural network that uses financial variables and market variables. In the study, prediction accuracy of the two models is compared. Through empirical results, it is found that when the Distance to Default (DD) is added, the credit rating of the third type of data can be effectively predicted. This is impossible to achieve using only the back propagation neural network with financial variables. After adding the Distance to Default (DD), it also increased the overall accuracy from 55.56% to 58.89%.
Reference:	一、中文部分王濟川、郭志剛，(2003)。Logistic迴歸模型-方法及應用，台北市：五南圖書。古永嘉、陳達新、陳維寧、楊延福，(2007)。以會計資訊衡量企業信用風險：區別分析與類神經網路模型之比較與應用。管理科學研究期刊，第四卷，第一期，第39-56頁。台灣金融研訓院編輯委員會，(2013)。巴賽爾資本協定三(Basel III) 實務應用。台北市：台灣金融研訓院。朱竣平(2006)。信用評等對公司違約率及財務危機預測之研究。真理大學財經研究所碩士論文。洪明欽、張揖平、陳昱陵、陳和貴，(2007)。信用評分模型區別力之穩健性研究。金融風險管理季刊，第三卷，第四期，第1-23頁。陳達新、周恆志，(2014)。財務風險管理(三版)：工具、衡量與未來發展。台北：雙葉書廊。許峻賓(2004)。KMV模型於預警系統之實證研究。真理大學財經研究所碩士論文。張大成、林郁翎、林修逸，(2007)。應用市場資訊於企業危機預警之研究。運籌與管理學刊，6(1)，1-18。黃明祥、許光華、黃榮彬、陳鈺玲，(2005)。KMV模型在台灣金融機構信用風險管理機制有效性之研究。財金論文叢刊，第三期，第29-50頁。單良、蒙志偉、郭姣君、王慧喧，(2010)。信用評等模型的12堂課—以消費金融為例。台北市：台灣金融研訓院。葉怡成，(2001)。應用類神經網路。台北：儒林圖書有限公司。羅聖雅(2006)。台灣地區上市公司信用風險衡量與績效評估。銘傳大學經濟學系碩士在職專班碩士論文。蘇敏賢、林修葳，(2006)。Merton模型預測違約之使用限制探索。金融風險管理季刊，第二捲，第三期，第65-87頁。二、英文部分 Altman, E. I. (1968). “Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy.” Journal of Finance, 23(4), 589-609. Altman, E. I., Haldeman, R.G., and Narayanan, P. (1977). “Zeta Analysis—A New Model to Indentify Bankruptcy Risk of Corporations.” Journal of Banking and Finance, Vol.1, 29-54. Atiya, A. F. (2001). “Bankruptcy Prediction for Credit Risk Using Neural Networks: Asurvey and New Results.” IEEE Transactions on Neural Networks, 12(4), 929-935. Beaver, W. H. (1966). “Financial Ratios as Predictors of Failure.” Journal of Accounting Research, 4, 71-111. Black, F. and Scholes M. (1973). “The Pricing of Options and Corporate Liabilities.” Journal of Political Economy, 81(3), 637-654. Fitzpartrick, P. J. (1932).“A Comparison of Ratios of Successful Industrial Enterprises with Those of Failed Firms.” Certified Public Accountant, 3: 656-662. Leshno, M. and Spector Y. (1996). “Neural Network Prediction Analysis: The Bankruptcy Case.” Neurocomputing, 10(2), 125-147. Merton, R. C. (1973). “Theory of Rational Option Pricing.” Bell Journal of Economics and Management Science 4, 141-183. Merton, R. C. (1974). “On the Pricing of Corporate Debt: The Risk Structure of Interest Rates.” Journal of Finance, 29(2), 449-470. Ohlson, J. A. (1980). “Financial Ratios and the Probabilistic Prediction of Bankruptcy.” Journal of Accounting Research, 18(1), 109-131. Zmijewski, M. E. (1984). “Methodological Issues Related to the Estimation of Financial Distress Prediction Models.” Journal of Accounting Research, 22, 59-82.
Description:	碩士國立政治大學金融學系 105352016
Source URI:	http://thesis.lib.nccu.edu.tw/record/#G0105352016
Data Type:	thesis
DOI:	10.6814/THE.NCCU.MB.008.2018.F06
Appears in Collections:	[Department of Money and Banking] Theses

Files in This Item:

There are no files associated with this item.

社群 sharing

Loading...