發(fā)布時(shí)間：2018-01-01 23:04

  本文關(guān)鍵詞：P2P網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)評(píng)級(jí)研究　出處：《北方工業(yè)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 信用風(fēng)險(xiǎn) 網(wǎng)貸平臺(tái) 風(fēng)險(xiǎn)評(píng)級(jí) 機(jī)器學(xué)習(xí)

【摘要】：作為互聯(lián)網(wǎng)金融的重要組成部分,P2P網(wǎng)絡(luò)借貸在我國(guó)得到快速的發(fā)展,網(wǎng)貸平臺(tái)數(shù)量不斷增加,但是在監(jiān)管缺失的環(huán)境下,問題平臺(tái)層出不窮,給整個(gè)網(wǎng)貸行業(yè)發(fā)展和社會(huì)穩(wěn)定帶來了巨大的負(fù)面影響。本文在信用風(fēng)險(xiǎn)評(píng)級(jí)理論基礎(chǔ)上,借鑒企業(yè)和銀行的信用風(fēng)險(xiǎn)評(píng)級(jí)方法,結(jié)合網(wǎng)貸平臺(tái)的特點(diǎn),選擇Credit Metrics模型作為研究方法。在不同時(shí)間點(diǎn)分別對(duì)網(wǎng)貸平臺(tái)做信用評(píng)級(jí),建立信用風(fēng)險(xiǎn)轉(zhuǎn)移矩陣。對(duì)網(wǎng)貸平臺(tái)做信用風(fēng)險(xiǎn)評(píng)級(jí)時(shí),首先分析了網(wǎng)貸平臺(tái)的運(yùn)營(yíng)模式和盈利模式,結(jié)合評(píng)級(jí)機(jī)構(gòu)的指標(biāo)體系,選擇反映網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)的指標(biāo)。其次分別使用非監(jiān)督學(xué)習(xí)中的聚類分析方法和有監(jiān)督學(xué)習(xí)中的決策樹、SVM和提升算法對(duì)網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)進(jìn)行衡量。在未知網(wǎng)貸平臺(tái)是否違約時(shí),使用聚類分析方法對(duì)網(wǎng)貸平臺(tái)做分類,根據(jù)指標(biāo)選擇確定各類別的信用等級(jí),完成網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)評(píng)級(jí),并對(duì)結(jié)果進(jìn)行跟蹤,結(jié)果表明:研究的網(wǎng)貸平臺(tái)樣本中,出現(xiàn)違約的平臺(tái)占7%左右,且都是評(píng)級(jí)結(jié)果較低的平臺(tái),借貸利率與評(píng)級(jí)結(jié)果呈負(fù)相關(guān)。在獲得問題平臺(tái)樣本后,使用決策樹、SVM和提升算法對(duì)網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)做評(píng)級(jí),結(jié)果顯示:有監(jiān)督學(xué)習(xí)算法優(yōu)于聚類分析,同時(shí)該類算法可實(shí)現(xiàn)對(duì)網(wǎng)貸平臺(tái)信用風(fēng)險(xiǎn)的預(yù)測(cè),其中提升算法的準(zhǔn)確率高。使用主成分分析對(duì)同樣的網(wǎng)貸平臺(tái)樣本做評(píng)級(jí),準(zhǔn)確率沒有聚類分析高。使用Adaboost算法對(duì)網(wǎng)貸平臺(tái)借款人的信用風(fēng)險(xiǎn)做研究,完善網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)評(píng)級(jí)。最后使用提升算法得到的信用風(fēng)險(xiǎn)評(píng)級(jí)結(jié)果,建立網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)轉(zhuǎn)移矩陣。加入回收率,衡量網(wǎng)貸平臺(tái)違約后的償還能力。信用風(fēng)險(xiǎn)轉(zhuǎn)移矩陣表征網(wǎng)貸平臺(tái)的違約概率,結(jié)合回收率,可預(yù)估網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)大小。研究結(jié)果顯示:利率的大小和評(píng)級(jí)結(jié)果呈反向關(guān)系,借款利率越低,網(wǎng)貸平臺(tái)的信用等級(jí)越高,相反則越低。對(duì)網(wǎng)貸平臺(tái)的信用風(fēng)險(xiǎn)的評(píng)級(jí),可預(yù)估網(wǎng)貸平臺(tái)違約的風(fēng)險(xiǎn)大小和整個(gè)行業(yè)的潛在風(fēng)險(xiǎn),使監(jiān)管部門更好的管理網(wǎng)貸平臺(tái),防范網(wǎng)貸行業(yè)風(fēng)險(xiǎn)的發(fā)生,同時(shí)可為投資者提供決策參考。
[Abstract]:As an important part of Internet finance, P2P network lending has been developing rapidly in China. The number of network lending platforms is increasing, but in the environment of lack of supervision, problem platforms emerge in endlessly. On the basis of the credit risk rating theory, this paper draws lessons from the credit risk rating methods of enterprises and banks, combined with the characteristics of the network lending platform. The Credit Metrics model is chosen as the research method. The credit rating of the network loan platform is done at different time points, and the credit risk transfer matrix is established. When the credit risk rating of the network loan platform is made, the credit risk rating of the network loan platform is made. First of all, it analyzes the operation model and profit model of the network loan platform, combined with the index system of the rating agencies. Select the index which reflects the credit risk of the network loan platform. Secondly, use the clustering analysis method in the unsupervised learning and the decision tree in the supervised learning. SVM and upgrade algorithm to measure the credit risk of the network loan platform. In the unknown network loan platform default, the use of clustering analysis to classify the network loan platform, according to the selection of indicators to determine the credit rating of each category. Complete the credit risk rating of the network loan platform, and track the results, the results show that: in the sample of the network loan platform, the default of the platform accounted for about 7%, and are the lower rating platform. The loan interest rate is negatively correlated with the rating results. After obtaining the sample of the problem platform, the credit risk of the network loan platform is rated using decision tree SVM and upgrade algorithm. The results show that the supervised learning algorithm is better than the clustering analysis, and this kind of algorithm can predict the credit risk of the network loan platform. Among them, the accuracy of the improved algorithm is high. Using principal component analysis (PCA), the sample of the same network loan platform is rated. The accuracy of clustering analysis is not high. Adaboost algorithm is used to study the credit risk of loan platform borrowers. Finally, using the credit risk rating results obtained by the upgrade algorithm, the credit risk transfer matrix of the network loan platform is established, and the recovery rate is added. The credit risk transfer matrix represents the default probability of the net loan platform, combined with the recovery rate. The research results show that the size of interest rate and rating results show a reverse relationship, the lower the borrowing rate, the higher the credit rating of the network lending platform. On the other hand, the lower the credit risk rating of the network loan platform, the risk of default and the potential risk of the whole industry can be estimated, so that the regulatory authorities can better manage the network loan platform. To prevent the occurrence of network loan industry risks, and to provide investors with decision-making reference.
【學(xué)位授予單位】：北方工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：F832.4;F724.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 徐榮貞;殷元星;王帥;;P2P網(wǎng)絡(luò)借貸平臺(tái)運(yùn)營(yíng)模式及風(fēng)險(xiǎn)控制思考——基于信息不對(duì)稱視角[J];財(cái)會(huì)月刊;2017年05期

2 李琪;王振;;P2P網(wǎng)貸平臺(tái)風(fēng)險(xiǎn)和標(biāo)的風(fēng)險(xiǎn)的辨析[J];上海金融;2016年10期

3 嚴(yán)復(fù)雷;李浩然;;P2P網(wǎng)貸平臺(tái)信用風(fēng)險(xiǎn)影響因素分析[J];西南金融;2016年10期

4 李戰(zhàn)江;句芳;修長(zhǎng)柏;喬光華;;銀行信用風(fēng)險(xiǎn)小樣本評(píng)級(jí)模型的構(gòu)建[J];統(tǒng)計(jì)與決策;2016年09期

5 王丹;張洪潮;;P2P網(wǎng)貸平臺(tái)信用風(fēng)險(xiǎn)評(píng)級(jí)模型構(gòu)建[J];財(cái)會(huì)月刊;2016年09期

6 于曉虹;樓文高;;基于隨機(jī)森林的P2P網(wǎng)貸信用風(fēng)險(xiǎn)評(píng)價(jià)、預(yù)警與實(shí)證研究[J];金融理論與實(shí)踐;2016年02期

7 王珂;孟海麗;楊全;;模糊Credit Metrics模型及其在信用風(fēng)險(xiǎn)評(píng)估中的應(yīng)用[J];金融理論與實(shí)踐;2016年02期

8 楊秀云;蔣園園;段珍珍;;KMV模型在我國(guó)商業(yè)銀行信用風(fēng)險(xiǎn)管理中的適用性分析及實(shí)證檢驗(yàn)[J];財(cái)經(jīng)理論與實(shí)踐;2016年01期

9 李琦;曹國(guó)華;;基于Credit Risk+模型的互聯(lián)網(wǎng)金融信用風(fēng)險(xiǎn)估計(jì)[J];統(tǒng)計(jì)與決策;2015年19期

10 李敏芳;田晨君;;基于因子分析法的我國(guó)P2P網(wǎng)貸平臺(tái)評(píng)級(jí)研究[J];湖北經(jīng)濟(jì)學(xué)院學(xué)報(bào)(人文社會(huì)科學(xué)版);2015年06期

，

本文編號(hào)：1366580