本文選題：信用風(fēng)險(xiǎn) + 商業(yè)銀行　； 參考：《成都理工大學(xué)》2017年碩士論文

【摘要】：信用風(fēng)險(xiǎn)作為商業(yè)銀行面臨的主要風(fēng)險(xiǎn)之一,一旦發(fā)生,不僅會(huì)造成商業(yè)銀行經(jīng)營(yíng)損失,甚至引發(fā)商業(yè)銀行破產(chǎn)危機(jī)。因此,如何對(duì)商業(yè)銀行信用風(fēng)險(xiǎn)進(jìn)行預(yù)警分析,進(jìn)而采取行之有效的手段提前防范與控制信用風(fēng)險(xiǎn),成為了當(dāng)前理論與實(shí)務(wù)界探討的熱點(diǎn)問題之一。就中國商業(yè)銀行而言,起步較晚,發(fā)展時(shí)間較短,在信用風(fēng)險(xiǎn)管理方面還缺少經(jīng)驗(yàn)。同時(shí),隨著中國資本市場(chǎng)的逐步開放,國外資本不斷涌入中國,在加快中國資本市場(chǎng)發(fā)展的同時(shí),也很可能對(duì)中國脆弱的商業(yè)銀行信用風(fēng)險(xiǎn)體系形成潛在威脅。因此,優(yōu)化信用風(fēng)險(xiǎn)預(yù)警方法,提升信用風(fēng)險(xiǎn)管理水平,完善信用風(fēng)險(xiǎn)管理體系,對(duì)中國商業(yè)銀行發(fā)展具有重要意義。基于上述分析,本論文以中國商業(yè)銀行的貸款企業(yè),即滬深兩市的部分上市公司為研究對(duì)象,基于中國金融的現(xiàn)實(shí)環(huán)境,選擇出16項(xiàng)誘發(fā)商業(yè)銀行爆發(fā)信用風(fēng)險(xiǎn)的指標(biāo)變量并進(jìn)行預(yù)處理,從而獲得14項(xiàng)能夠顯著區(qū)分中國商業(yè)銀行信用風(fēng)險(xiǎn)與非信用風(fēng)險(xiǎn)樣本的指標(biāo)變量,進(jìn)而運(yùn)用核主成分分析(KPCA)方法對(duì)這14項(xiàng)指標(biāo)變量進(jìn)行提取,以消除指標(biāo)變量間的高相關(guān)性特征;引入支持向量機(jī)(SVM)人工智能技術(shù),構(gòu)建商業(yè)銀行信用風(fēng)險(xiǎn)的SVM智能預(yù)警模型,并運(yùn)用粒子群優(yōu)化(PSO)方法優(yōu)化SVM模型的參數(shù),以此來開展信用風(fēng)險(xiǎn)預(yù)警的研究工作,并通過實(shí)驗(yàn)證明了本論文提出的KPCA-PSO-SVM模型在商業(yè)銀行信用風(fēng)險(xiǎn)預(yù)警中的優(yōu)異的預(yù)測(cè)性能。本論文的主要研究?jī)?nèi)容如下:1.對(duì)風(fēng)險(xiǎn)預(yù)預(yù)警樣本的預(yù)處理研究。由于直接基于樣本的原始指標(biāo)變量來構(gòu)建預(yù)警模型存在諸多問題,因此,本論文運(yùn)用了歸一化處理方法和統(tǒng)計(jì)分析方法對(duì)原始的指標(biāo)變量進(jìn)行了篩選。通過實(shí)證結(jié)果表明,運(yùn)用歸一化方法能夠?qū)⒏髦笜?biāo)變量轉(zhuǎn)換為正態(tài)分布,從而能夠消除指標(biāo)變量的量綱問題;運(yùn)用統(tǒng)計(jì)分析方法發(fā)現(xiàn),營(yíng)業(yè)收入增長(zhǎng)率和稅后利潤(rùn)增長(zhǎng)率兩項(xiàng)指標(biāo)變量無法顯著區(qū)分信用風(fēng)險(xiǎn)與非信用風(fēng)險(xiǎn)樣本,因而需要將其從指標(biāo)變量中刪除。通過實(shí)驗(yàn),本論文就獲得了具有無量綱特征、能夠顯著區(qū)分信用風(fēng)險(xiǎn)與非信用風(fēng)險(xiǎn)樣本的指標(biāo)變量。2.對(duì)指標(biāo)變量提取方法進(jìn)行研究。誘發(fā)商業(yè)銀行爆發(fā)信用風(fēng)險(xiǎn)的指標(biāo)變量眾多,且這些變量之間往往呈現(xiàn)高相關(guān)性特征。如果不消除這些變量的高相關(guān)特征而直接運(yùn)用其進(jìn)行建模,則很容易引發(fā)數(shù)據(jù)冗余問題,最終降低SVM智能預(yù)警模型的預(yù)測(cè)效果。因此,本論文引入了常用的主成分分析方法(PCA)以及其改進(jìn)方法——核主成分分析方法(KPCA)進(jìn)行了實(shí)證對(duì)比研究。實(shí)證結(jié)果表明,KPCA方法在指標(biāo)提取上較PCA方法更為高效,同時(shí),與SVM相結(jié)合,KPCA能夠顯著地提升SVM的預(yù)測(cè)效果,然而PCA方法卻會(huì)降低SVM的預(yù)測(cè)效果。從而表明,銀行信用風(fēng)險(xiǎn)預(yù)警指標(biāo)變量存在非線性特征,而KPCA方法正好能夠提取指標(biāo)變量的非線性特征,能夠有效地提升SVM的預(yù)警能力。3.對(duì)SVM參數(shù)優(yōu)化方法研究。SVM智能預(yù)警模型的預(yù)測(cè)能力在很大程度上取決于懲罰參數(shù)和核函數(shù)參數(shù),如果不恰當(dāng)?shù)剡x擇這兩類參數(shù),就很可能導(dǎo)致SVM模型出現(xiàn)過擬合或欠擬合。為此,本論文對(duì)比研究了以網(wǎng)格尋優(yōu)法(GS)為代表的傳統(tǒng)參數(shù)優(yōu)化方法和以遺傳算法(GA)、粒子群算法(PSO)為代表的啟發(fā)式算法在SVM參數(shù)尋優(yōu)中的效果。實(shí)驗(yàn)結(jié)果表明,啟發(fā)式算法在參數(shù)尋優(yōu)上優(yōu)于傳統(tǒng)的GS參數(shù)尋優(yōu)方法,其中,以PSO為代表的啟發(fā)式算法又比以GA為代表的啟發(fā)式算法具有更為優(yōu)異的預(yù)測(cè)性能,能夠更為有效地提升SVM預(yù)警模型的預(yù)測(cè)性能。通過上述一系列實(shí)驗(yàn),本論文認(rèn)為,基于KPCA-PSO-SVM的商業(yè)銀行信用風(fēng)險(xiǎn)預(yù)警模型是商業(yè)銀行信用風(fēng)險(xiǎn)監(jiān)管部門應(yīng)對(duì)與防范信用風(fēng)險(xiǎn)的最優(yōu)的應(yīng)用工具。監(jiān)管部門能夠運(yùn)用本論文構(gòu)建的KPCA-PSO-SVM智能預(yù)警模型,對(duì)未來一段時(shí)間內(nèi)商業(yè)銀行的信用風(fēng)險(xiǎn)進(jìn)行全面而準(zhǔn)確的預(yù)測(cè),即時(shí)制定并實(shí)施應(yīng)對(duì)信用風(fēng)險(xiǎn)的相關(guān)政策措施,從而加強(qiáng)市場(chǎng)監(jiān)管,有效地防范信用風(fēng)險(xiǎn)。
[Abstract]:As one of the main risks faced by commercial banks, credit risk will not only cause business losses, but also lead to the bankruptcy crisis of commercial banks. Therefore, how to carry out early warning and Analysis on commercial banks' credit risk and then take effective measures to prevent and control credit risks has become the current theory and As far as China's commercial banks are concerned, China's commercial banks have a late start, a short development time and lack of experience in the management of credit risk. At the same time, with the gradual opening up of China's capital market, foreign capital is constantly pouring into China, while the development of China's capital market is accelerated, and it is likely to be vulnerable to China's business. The bank credit risk system has a potential threat. Therefore, it is of great significance to optimize the early warning method of credit risk, improve the management level of credit risk and improve the credit risk management system. Based on the above analysis, this paper takes the loan enterprises of Chinese commercial banks, that is, some listed companies in Shanghai and Shenzhen two cities as the research. Based on the real environment of China's finance, we selected 16 indexes to induce the credit risk of commercial banks and pretreated them, so as to obtain 14 index variables that can distinguish between credit risk and non credit risk samples of Chinese commercial banks, and then use the nuclear principal component analysis (KPCA) method to enter the 14 index variables. In order to remove the high correlation characteristic between the index variables, we introduce the support vector machine (SVM) artificial intelligence technology to construct the SVM intelligent early warning model of the credit risk of commercial banks, and optimize the parameters of the SVM model by using the particle swarm optimization (PSO) method to carry out the research work of the credit risk early warning, and prove the thesis through the experiment. The outstanding performance of the KPCA-PSO-SVM model in the early warning of credit risk in commercial banks is proposed. The main contents of this paper are as follows: 1. research on Prewarning samples for risk prewarning. There are many questions in the construction of early warning model based on the original index variables based on the sample. Therefore, this paper uses the normalized processing party. The original index variables are screened by method and statistical analysis method. The empirical results show that the normalization method can convert the index variables into normal distribution and can eliminate the dimensionless problem of the index variables. The statistical analysis method shows that the growth rate of revenue and the rate of profit growth after tax are two variables. The method clearly distinguishes the sample of credit risk and non credit risk, so it needs to be deleted from the index variable. Through the experiment, this paper obtains the dimensionless characteristics, which can distinguish between the index variable.2. of the credit risk and the non credit risk sample, and induces the credit risk of the commercial bank to break out. There are many index variables, and these variables often show high correlation characteristics. If they do not eliminate the high correlation characteristics of these variables and directly use them for modeling, it is easy to cause data redundancy and ultimately reduce the prediction effect of SVM intelligent early warning model. Therefore, this paper introduces the common principal component analysis method (PCA). The positive results show that the KPCA method is more efficient than the PCA method in the index extraction, and the KPCA can significantly improve the prediction effect of SVM, while PCA method can reduce the predictive effect of SVM, which indicates that the credit risk of the bank can be reduced by the PCA method. Thus, the bank credit risk is indicated by the PCA method. Therefore, the credit risk of the bank is shown to be the risk of the bank's credit risk. The early warning index variable has nonlinear characteristics, and the KPCA method just can extract the nonlinear characteristics of the index variables. It can effectively improve the early warning capability of the SVM.3.. The prediction ability of the SVM parameter optimization method for the.SVM intelligent early warning model depends largely on the penalty parameters and the kernel function parameters, if the two is not chosen properly. The class parameter is likely to lead to the over fitting or less fitting of the SVM model. Therefore, this paper compares the traditional parameter optimization method represented by the grid optimization (GS) and the effect of the heuristic algorithm represented by genetic algorithm (GA) and particle swarm optimization (PSO) in the optimization of SVM parameter optimization. The experimental results show that the heuristic algorithm is in the parameter. The optimization method is superior to the traditional GS parameter optimization method. Among them, the heuristic algorithm represented by PSO has more excellent predictive performance than the heuristic algorithm represented by GA, and it can improve the prediction performance of the SVM early warning model more effectively. Through a series of experiments above, this paper considers that the commercial bank credit based on KPCA-PSO-SVM is based on this series of experiments. The risk early warning model is the best application tool for the credit risk supervision department of commercial banks to deal with and prevent the credit risk. The supervisory department can use the KPCA-PSO-SVM intelligent early warning model constructed in this paper to make a comprehensive and accurate prediction for the credit risk of commercial banks in the future period, and make and implement the coping credit immediately. Risk related policies and measures to strengthen market supervision and effectively prevent credit risks.

【學(xué)位授予單位】：成都理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：F832.33

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 Qinwei Chi;Wenjing Li;;Economic policy uncertainty, credit risks and banks lending decisions: Evidence from Chinese commercial banks[J];China Journal of Accounting Research;2017年01期

2 魏海麗;周遠(yuǎn);;短期國際資本對(duì)金融穩(wěn)定動(dòng)態(tài)影響的實(shí)證分析[J];統(tǒng)計(jì)與決策;2016年19期

3 高波;任若恩;;基于主成分回歸模型的行業(yè)輪動(dòng)策略及其業(yè)績(jī)?cè)u(píng)價(jià)[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2016年19期

4 李燁;賈進(jìn)章;;基于改進(jìn)GS-SVM的煤礦沖擊地壓預(yù)測(cè)研究[J];世界科技研究與發(fā)展;2016年04期

5 王浩;郭瑞軍;;改進(jìn)PCA-BP神經(jīng)網(wǎng)絡(luò)模型在公路客運(yùn)量預(yù)測(cè)的應(yīng)用[J];大連交通大學(xué)學(xué)報(bào);2016年02期

6 張公讓;萬飛;;基于網(wǎng)格搜索的SVM在入侵檢測(cè)中的應(yīng)用[J];計(jì)算機(jī)技術(shù)與發(fā)展;2016年01期

7 田中大;李樹江;王艷紅;高憲文;;基于KPCA優(yōu)化ESN的網(wǎng)絡(luò)流量預(yù)測(cè)方法[J];電機(jī)與控制學(xué)報(bào);2015年12期

8 蔣_g;高瑜;;基于KMV模型的中國上市公司信用風(fēng)險(xiǎn)評(píng)估研究[J];中央財(cái)經(jīng)大學(xué)學(xué)報(bào);2015年09期

9 肖斌卿;楊e，

本文編號(hào)：1828031