本文選題：借款人信用評(píng)估 + P2P網(wǎng)絡(luò)借貸��； 參考：《哈爾濱工業(yè)大學(xué)》2017年碩士論文

【摘要】：P2P網(wǎng)絡(luò)借貸進(jìn)入中國(guó)已有10余年的時(shí)間,目前已成為個(gè)人以及中小微企業(yè)進(jìn)行融資的重要渠道。2016年全年,我國(guó)網(wǎng)絡(luò)借貸平臺(tái)的累計(jì)數(shù)量已達(dá)5877家,而正常運(yùn)營(yíng)的平臺(tái)數(shù)量卻只有2448家,平臺(tái)成交量卻達(dá)到了20638.72億元,行業(yè)總體貸款余額更是高達(dá)8162.24億元。雖然正常運(yùn)營(yíng)贏(yíng)得平臺(tái)有所減少,但是相較2015年去年的成交量與貸款余額分別增長(zhǎng)110%和100.99%,表明P2P網(wǎng)絡(luò)借貸還是解決融資問(wèn)題的一種重要方式。近年,隨著我國(guó)互聯(lián)網(wǎng)金融整改行動(dòng)的逐步深入,我國(guó)網(wǎng)絡(luò)借貸行業(yè)的外部借貸環(huán)境逐步得到改善,但P2P網(wǎng)絡(luò)借貸的借款人信用風(fēng)險(xiǎn)問(wèn)題依然是影響網(wǎng)絡(luò)借貸行業(yè)發(fā)展的重要因素,且國(guó)內(nèi)大多數(shù)P2P網(wǎng)絡(luò)借貸平臺(tái)的信用評(píng)估方式都較為簡(jiǎn)單、評(píng)估性能也不大理想,對(duì)借款人的信用管理還有待加強(qiáng)。因此,本文通過(guò)隨機(jī)森林模型,結(jié)合翼龍貸的數(shù)據(jù),構(gòu)建了P2P借款人信用評(píng)估模型對(duì)P2P平臺(tái)中借款人存在的信用風(fēng)險(xiǎn)問(wèn)題進(jìn)行評(píng)估。本文在研究P2P借款人信用評(píng)估過(guò)程中,首先簡(jiǎn)要介紹了P2P網(wǎng)絡(luò)借貸的相關(guān)概念及發(fā)展現(xiàn)狀,其次對(duì)比介紹了隨機(jī)森林、支持向量機(jī)、Logistic回歸模型,確定隨機(jī)森林為本文P2P借款人信用評(píng)估所采用模型;最后結(jié)合翼龍貸數(shù)據(jù),確定P2P借款人信用評(píng)估指標(biāo)體系,并利用隨機(jī)森林構(gòu)建了P2P網(wǎng)絡(luò)借貸的借款人信用評(píng)估模型。在構(gòu)建隨機(jī)森林模型過(guò)程中,首先參照其他P2P網(wǎng)絡(luò)借貸地相關(guān)研究初步選取了影響借款人信用風(fēng)險(xiǎn)評(píng)估19項(xiàng)指標(biāo);其次利用隨機(jī)森林特征選取方法篩選出8項(xiàng)指標(biāo)作為本文P2P借款人信用評(píng)估指標(biāo)體系;然后利用R語(yǔ)言分別構(gòu)建了隨機(jī)森林和支持向量機(jī),并對(duì)其分類(lèi)性能進(jìn)行了比較分析。實(shí)證結(jié)果表明,隨機(jī)森林特征選擇能有效地篩選指標(biāo),且發(fā)現(xiàn)在P2P網(wǎng)絡(luò)借貸的信用評(píng)估方面,隨機(jī)森林模型具有更好的分類(lèi)性能。通過(guò)分析指標(biāo)篩選結(jié)果與實(shí)證結(jié)果還發(fā)現(xiàn),借款人在平臺(tái)中的里斯借款記錄及借款信息都是影響P2P網(wǎng)絡(luò)借貸借款人信用風(fēng)險(xiǎn)的重要觀(guān)測(cè)指標(biāo)。
[Abstract]:P2P network lending has been in China for more than 10 years and has become an important channel for individuals and small and medium-sized enterprises to raise funds. In all of 2016, the total number of online lending platforms in China has reached 5877. But the normal operating platform number is only 2448, the platform turnover has reached 2.063872 trillion yuan, the industry overall loan balance is as high as 816.224 billion yuan. Although the normal operation won platform has been reduced, the volume of transactions and loan balance rose 110 percent and 100.99 percent, respectively, compared with last year in 2015, indicating that P2P network lending is also an important way to solve the financing problem. In recent years, with the gradual deepening of China's Internet financial reform, the external lending environment of China's network lending industry has been gradually improved. However, the credit risk of the borrowers of P2P network lending is still an important factor affecting the development of the network lending industry, and most of the domestic P2P network lending platform credit evaluation methods are relatively simple, the evaluation performance is not ideal. The credit management of borrowers needs to be strengthened. Therefore, based on the random forest model and pterosaurus data, this paper constructs a P2P borrower credit evaluation model to evaluate the credit risk of the borrower in P2P platform. In the course of studying the credit evaluation of P2P borrowers, this paper firstly briefly introduces the related concepts and development status of P2P network lending, and then compares the stochastic forest, support vector machine and logistic regression model. The random forest is the model used in the credit evaluation of P2P borrowers. Finally, the credit evaluation index system of P2P borrowers is established with pterosaurus loan data, and the credit evaluation model of P2P borrowers is constructed by using random forests. In the process of constructing a stochastic forest model, 19 indexes of credit risk assessment of borrowers are preliminarily selected according to the relevant studies of other P2P network lending sites. Secondly, 8 indexes are selected by the random forest feature selection method as the credit evaluation index system of P2P borrowers, and then the random forest and support vector machine are constructed by using R language, and their classification performance is compared and analyzed. The empirical results show that the stochastic forest feature selection can effectively screen the index, and it is found that the stochastic forest model has better classification performance in the credit evaluation of P2P network lending. Through the analysis of the index screening results and the empirical results, it is also found that the loan records and loan information of the borrowers in the platform are important observation indicators that affect the credit risk of P2P network borrowers.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：F832.4;F724.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李思瑤;王積田;柳立超;;基于生存分析的P2P網(wǎng)絡(luò)借貸違約風(fēng)險(xiǎn)影響因素研究[J];經(jīng)濟(jì)體制改革;2016年06期

2 曾江洪;李文瀚;陳璽慧;;P2P借款的損失能挽回嗎?——基于拍拍貸的實(shí)證研究[J];科研管理;2016年08期

3 柳向東;李鳳;;大數(shù)據(jù)背景下網(wǎng)絡(luò)借貸的信用風(fēng)險(xiǎn)評(píng)估——以人人貸為例[J];統(tǒng)計(jì)與信息論壇;2016年05期

4 孫艷軍;;基于P2P金融模式變異法律性質(zhì)之論證構(gòu)建其監(jiān)管模式[J];中央財(cái)經(jīng)大學(xué)學(xué)報(bào);2016年03期

5 孫艷軍;;以英美監(jiān)管為鏡鑒構(gòu)建我國(guó)P2P普惠金融監(jiān)管體系[J];上海金融;2016年03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 吳佳哲;;基于羊群效應(yīng)的P2P網(wǎng)絡(luò)借貸模式研究[J];國(guó)際金融研究;2015年11期

8 李淵琦;陳芳;;我國(guó)P2P網(wǎng)貸的風(fēng)險(xiǎn)分析及監(jiān)管對(duì)策[J];上海金融;2015年07期

9 潘錫泉;;我國(guó)P2P網(wǎng)貸發(fā)展中蘊(yùn)含的風(fēng)險(xiǎn)及監(jiān)管思路[J];當(dāng)代經(jīng)濟(jì)管理;2015年04期

10 王長(zhǎng)江;楊金葉;;P2P網(wǎng)絡(luò)借貸的風(fēng)險(xiǎn)與監(jiān)管模式研究[J];經(jīng)濟(jì)縱橫;2015年04期

相關(guān)碩士學(xué)位論文 前2條

1 宋文;P2P網(wǎng)絡(luò)借貸行為的實(shí)證研究[D];上海交通大學(xué);2013年

2 張職;P2P網(wǎng)絡(luò)借貸平臺(tái)營(yíng)運(yùn)模式的比較、問(wèn)題及對(duì)策研究[D];華東理工大學(xué);2013年

，

本文編號(hào)：1851511