發(fā)布時(shí)間：2018-01-11 15:35

  本文關(guān)鍵詞：基于客戶細(xì)分的大學(xué)生網(wǎng)貸項(xiàng)目信用風(fēng)險(xiǎn)的識(shí)別與度量　出處：《上海師范大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 大學(xué)生網(wǎng)貸 信用風(fēng)險(xiǎn) 客戶細(xì)分 XGBoost

【摘要】：P2P小額借貸模式近幾年來發(fā)展迅速,截至2016年11月底,我國正常運(yùn)營(yíng)的P2P網(wǎng)貸平臺(tái)數(shù)量高達(dá)2534家,行業(yè)競(jìng)爭(zhēng)愈演愈烈,行業(yè)市場(chǎng)也開始出現(xiàn)細(xì)分。在眾多的細(xì)分市場(chǎng)中,大學(xué)生P2P網(wǎng)貸發(fā)展迅猛,獨(dú)樹一幟。大學(xué)生相對(duì)于其他網(wǎng)貸借款人,有著身份易認(rèn)證、違約成本高、父母為其潛在擔(dān)保等優(yōu)勢(shì),信用風(fēng)險(xiǎn)相對(duì)較小。但是,由于網(wǎng)貸簡(jiǎn)單便捷導(dǎo)致沖動(dòng)消費(fèi)、大學(xué)生沒有固定的經(jīng)濟(jì)來源、征信意識(shí)不強(qiáng)等原因,大學(xué)生網(wǎng)貸平臺(tái)上仍存在大量的逾期違約現(xiàn)象。本文主要是策劃與實(shí)施一個(gè)大學(xué)生網(wǎng)貸項(xiàng)目信用風(fēng)險(xiǎn)識(shí)別與度量方案。本方案實(shí)施與驗(yàn)證均是基于“速溶360”平臺(tái)項(xiàng)目信息。本方案實(shí)施主要包含4個(gè)步驟:首先,基于客戶細(xì)分理論,分別從新老客戶、借款者學(xué)歷兩個(gè)方面對(duì)大學(xué)生網(wǎng)貸項(xiàng)目進(jìn)行分類,利用兩步聚類法根據(jù)借款者學(xué)歷將人群分為了3類:高學(xué)歷人群、普通人群以及低學(xué)歷人群;其次,針對(duì)每個(gè)類群項(xiàng)目,利用特征選擇方法,進(jìn)行降維處理,提高了后續(xù)方法的準(zhǔn)確性與穩(wěn)定性;然后,利用XGBoost算法,對(duì)每個(gè)類群的網(wǎng)貸項(xiàng)目信用風(fēng)險(xiǎn)進(jìn)行識(shí)別,結(jié)果顯示,該算法在信用風(fēng)險(xiǎn)識(shí)別上的運(yùn)用效果很好,準(zhǔn)確率很高;最后,利用XGBoost模型結(jié)果與評(píng)分卡模型對(duì)網(wǎng)貸項(xiàng)目的信用風(fēng)險(xiǎn)進(jìn)行度量并檢驗(yàn)結(jié)果的有效性。本方案的實(shí)施效果很好,符合預(yù)期,是一個(gè)較好的信用風(fēng)險(xiǎn)識(shí)別方案。此外,本方案的設(shè)計(jì)與實(shí)施,不僅為網(wǎng)貸項(xiàng)目信用風(fēng)險(xiǎn)識(shí)別提供了一種新的思路,也驗(yàn)證了 XGBoost模型在信用風(fēng)險(xiǎn)識(shí)別問題上的有效性。
[Abstract]:Peer-to-peer microfinance model has developed rapidly in recent years. By the end of November 2016, the number of P2P network lending platforms in China is as high as 2534, and the competition in the industry is becoming more and more intense. Industry market also began to subdivide. In many segments of the market, P2P network loans for college students developed rapidly, unique. Compared with other network loan borrowers, college students have easy identity authentication, high cost of breach of contract. Parents for its potential guarantee and other advantages, credit risk is relatively small. However, because of the simple and convenient Internet loans led to impulse consumption, college students do not have a fixed source of financial resources, credit awareness is not strong and other reasons. There is still a large number of overdue breach of contract on the university student network loan platform. This paper mainly plans and implements a scheme to identify and measure the credit risk of the university student network loan project. The implementation and verification of this scheme are all based on " Instant 360 "platform project information. The implementation of this scheme mainly includes four steps: first. Based on the theory of customer segmentation, this paper classifies college students' online loan projects from two aspects: new and old customers, borrowers' qualifications, and classifies the population into three categories according to the borrower's degree by using two-step clustering method: the high-educated group. The general population and the low-educated population; Secondly, the method of feature selection is used to reduce the dimension of each group item, which improves the accuracy and stability of the follow-up method. Then, the XGBoost algorithm is used to identify the credit risk of each network loan project. The results show that the algorithm is effective and accurate in the identification of credit risk. Finally, using the XGBoost model results and scoring card model to measure the credit risk of network loan projects and test the effectiveness of the results. The implementation of this scheme is very good, in line with expectations. In addition, the design and implementation of this scheme not only provides a new way to identify the credit risk of the network loan project. The validity of XGBoost model in credit risk identification is also verified.
【學(xué)位授予單位】：上海師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：G645.5;F724.6;F832.4

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 蔡_g;;大學(xué)生網(wǎng)貸的現(xiàn)狀及策略[J];現(xiàn)代經(jīng)濟(jì)信息;2016年15期

2 王東靜;張社爭(zhēng);;大學(xué)生網(wǎng)貸消費(fèi)心理探析[J];榆林學(xué)院學(xué)報(bào);2016年04期

3 孟潔浩;;我國P2P網(wǎng)貸行業(yè)發(fā)展現(xiàn)狀研究[J];商;2016年23期

4 鄧秀煥;;大學(xué)生信貸消費(fèi)市場(chǎng)前景分析[J];現(xiàn)代商業(yè);2015年17期

5 陳海斌;;我國P2P網(wǎng)貸行業(yè)的現(xiàn)狀及發(fā)展[J];時(shí)代金融;2015年14期

6 李君藝;張宇華;;商業(yè)銀行信用風(fēng)險(xiǎn)評(píng)估實(shí)證分析及方法比較[J];網(wǎng)絡(luò)安全技術(shù)與應(yīng)用;2013年03期

7 解治宇;;基于人群的汽車市場(chǎng)細(xì)分模型及其應(yīng)用[J];北京汽車;2012年05期

8 楊新求;;我國P2P網(wǎng)絡(luò)借貸運(yùn)營(yíng)模式簡(jiǎn)析[J];知識(shí)經(jīng)濟(jì);2012年05期

9 王紫薇;袁中華;鐘鑫;;中國P2P網(wǎng)絡(luò)小額信貸運(yùn)營(yíng)模式研究——基于“拍拍貸”、“宜農(nóng)貸”的案例分析[J];新金融;2012年02期

10 馬運(yùn)全;;P2P網(wǎng)絡(luò)借貸的發(fā)展、風(fēng)險(xiǎn)與行為矯正[J];新金融;2012年02期

相關(guān)碩士學(xué)位論文 前2條

1 林于力;信用風(fēng)險(xiǎn)評(píng)估模型研究[D];重慶大學(xué);2014年

2 徐暉;多元統(tǒng)計(jì)方法在市場(chǎng)細(xì)分中的應(yīng)用[D];華南理工大學(xué);2013年

，

本文編號(hào)：1410158