基于決策樹算法的P2P網(wǎng)貸借款人違約風(fēng)險(xiǎn)度量研究
發(fā)布時(shí)間：2018-08-08 12:51
【摘要】：自2007年引入中國,互聯(lián)網(wǎng)金融主要模式之一的P2P網(wǎng)絡(luò)借貸,憑借著其低門檻、操作簡(jiǎn)便等諸多優(yōu)勢(shì)得到了爆發(fā)式發(fā)展。據(jù)統(tǒng)計(jì),截至2015年12月31日,我國已有2959家正常運(yùn)營的網(wǎng)貸平臺(tái),且仍在迅猛發(fā)展中。在準(zhǔn)入門檻低、行業(yè)標(biāo)準(zhǔn)缺失、監(jiān)管不力等行業(yè)發(fā)展背景下,平臺(tái)跑路、停業(yè)等問題數(shù)見不鮮。2015年12月底,累計(jì)有1263家問題網(wǎng)貸平臺(tái),僅12月新增問題平臺(tái)環(huán)比增長27家。其中,跑路及停業(yè)平臺(tái)數(shù)量占比87.74%,其平均經(jīng)營時(shí)間較長(13.78個(gè)月),可見跑路平臺(tái)中純?cè)p騙平臺(tái)并不多,主要還是平臺(tái)自身運(yùn)營出現(xiàn)問題。P2P網(wǎng)絡(luò)借貸業(yè)務(wù)面臨的信用風(fēng)險(xiǎn)、技術(shù)風(fēng)險(xiǎn)、法律風(fēng)險(xiǎn)等眾多風(fēng)險(xiǎn)類型中,最關(guān)鍵的是信用風(fēng)險(xiǎn),即借款人違約風(fēng)險(xiǎn)。本文旨在研究在監(jiān)管正規(guī)有力、法律健全無漏洞的市場(chǎng)環(huán)境下,網(wǎng)貸平臺(tái)自身度量借款人違約風(fēng)險(xiǎn)的方法。限于現(xiàn)階段我國P2P行業(yè)數(shù)據(jù)積累的不完善性和平臺(tái)借款人詳細(xì)數(shù)據(jù)交易的非公開性等多種因素,本文所選作為實(shí)證分析的數(shù)據(jù)來自目前美國最大的P2P網(wǎng)絡(luò)借貸平臺(tái)“Lending Club”網(wǎng)站,其網(wǎng)站上借款人信息數(shù)據(jù)披露充分且準(zhǔn)確。本文站在P2P平臺(tái)控制風(fēng)險(xiǎn)的角度,研究借款人這一角色的違約風(fēng)險(xiǎn)度量方法,利用Lending Club網(wǎng)站上公布的借款人詳細(xì)交易數(shù)據(jù),選取出若干備選風(fēng)險(xiǎn)特征與變量,通過數(shù)據(jù)抽取、數(shù)據(jù)轉(zhuǎn)換、過采樣、數(shù)據(jù)離散化等方法對(duì)數(shù)據(jù)進(jìn)行預(yù)處理,并借助信息增益率技術(shù)篩選出最終建模特征變量,繼而在Weka平臺(tái)上構(gòu)建C4.5決策樹信用風(fēng)險(xiǎn)度量模型。通過混淆矩陣、ROC曲線、AUC值等評(píng)估指標(biāo)得出構(gòu)建的決策樹風(fēng)險(xiǎn)度量模型具有較好的解釋力的結(jié)論。在此基礎(chǔ)上,本文還采用Bagging,Adaboost集成學(xué)習(xí)方法對(duì)C4.5基本決策樹模型進(jìn)行改進(jìn)與提升,取得了很好的度量效果。雖然選取的是國外數(shù)據(jù),但是其方法和結(jié)論仍具有一定參考意義。文章最后基于決策樹違約風(fēng)險(xiǎn)評(píng)估研究結(jié)果對(duì)完善平臺(tái)借款人征信體系提出了一些改進(jìn)意見。
[Abstract]:Since it was introduced into China in 2007, P2P network lending, one of the main modes of Internet finance, has been explosively developed with its advantages of low threshold and easy operation. According to statistics, as of December 31, 2015, there are 2959 normal network loan platforms in China, and they are still developing rapidly. Under the background of low entry threshold, lack of industry standards, weak supervision and other industry development, the number of problems such as platform running and shutting down is not new. At the end of December 2015, there were 1263 problem net loan platforms, 27 new problem platforms were added in December only. Among them, the number of running and shutting down platforms accounts for 87.74 percent, and its average operating time is relatively long (13.78 months). It can be seen that there are not many pure fraud platforms in the running road platform, mainly because of the credit risks faced by the platform's own operation problems and P2P network lending business. Among the various risk types, such as technical risk and legal risk, credit risk is the most critical, that is, borrower default risk. The purpose of this paper is to study the method of measuring the borrower's default risk in the market environment where the formal supervision is effective and the law is sound and there are no loopholes. Limited to many factors, such as the imperfection of data accumulation in P2P industry in our country at present and the non-disclosure of detailed data transactions of platform borrowers, The data selected in this paper as an empirical analysis come from the Lending Club website, the largest P2P network lending platform in the United States at present. The information disclosure of borrowers on the website is full and accurate. From the point of view of controlling risk on P2P platform, this paper studies the measurement method of default risk in the role of borrower. By using the detailed transaction data of borrower published on Lending Club website, this paper selects a number of alternative risk characteristics and variables and extracts them through data extraction. Data conversion, oversampling and data discretization are used to preprocess the data, and the final modeling feature variables are screened by the information gain rate technique, and then the credit risk measurement model of C4.5 decision tree is constructed on Weka platform. Based on the ROC curve and AUC value of confusion matrix, it is concluded that the risk measurement model of decision tree has good explanatory power. On this basis, we also improve and improve the basic decision tree model of C4.5 by using the BaggingsAdaboost ensemble learning method, and obtain a good measurement effect. Although foreign data are selected, its methods and conclusions still have some reference significance. Finally, based on the research results of decision tree default risk assessment, some suggestions are put forward to improve the platform borrower credit system.
【學(xué)位授予單位】：湖南師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：F724.6;F832.4;TP18
本文編號(hào)：2171832
[Abstract]:Since it was introduced into China in 2007, P2P network lending, one of the main modes of Internet finance, has been explosively developed with its advantages of low threshold and easy operation. According to statistics, as of December 31, 2015, there are 2959 normal network loan platforms in China, and they are still developing rapidly. Under the background of low entry threshold, lack of industry standards, weak supervision and other industry development, the number of problems such as platform running and shutting down is not new. At the end of December 2015, there were 1263 problem net loan platforms, 27 new problem platforms were added in December only. Among them, the number of running and shutting down platforms accounts for 87.74 percent, and its average operating time is relatively long (13.78 months). It can be seen that there are not many pure fraud platforms in the running road platform, mainly because of the credit risks faced by the platform's own operation problems and P2P network lending business. Among the various risk types, such as technical risk and legal risk, credit risk is the most critical, that is, borrower default risk. The purpose of this paper is to study the method of measuring the borrower's default risk in the market environment where the formal supervision is effective and the law is sound and there are no loopholes. Limited to many factors, such as the imperfection of data accumulation in P2P industry in our country at present and the non-disclosure of detailed data transactions of platform borrowers, The data selected in this paper as an empirical analysis come from the Lending Club website, the largest P2P network lending platform in the United States at present. The information disclosure of borrowers on the website is full and accurate. From the point of view of controlling risk on P2P platform, this paper studies the measurement method of default risk in the role of borrower. By using the detailed transaction data of borrower published on Lending Club website, this paper selects a number of alternative risk characteristics and variables and extracts them through data extraction. Data conversion, oversampling and data discretization are used to preprocess the data, and the final modeling feature variables are screened by the information gain rate technique, and then the credit risk measurement model of C4.5 decision tree is constructed on Weka platform. Based on the ROC curve and AUC value of confusion matrix, it is concluded that the risk measurement model of decision tree has good explanatory power. On this basis, we also improve and improve the basic decision tree model of C4.5 by using the BaggingsAdaboost ensemble learning method, and obtain a good measurement effect. Although foreign data are selected, its methods and conclusions still have some reference significance. Finally, based on the research results of decision tree default risk assessment, some suggestions are put forward to improve the platform borrower credit system.
【學(xué)位授予單位】：湖南師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：F724.6;F832.4;TP18
【引證文獻(xiàn)】
相關(guān)期刊論文 前1條
1 程園園;劉勝題;;網(wǎng)絡(luò)借貸中借款方還款情況分析——基于多值選擇模型[J];電子商務(wù);2017年07期
，本文編號(hào)：2171832
本文鏈接：http://sikaile.net/jingjilunwen/guojimaoyilunwen/2171832.html
最近更新
教材專著
