發(fā)布時(shí)間：2018-01-07 15:08

  本文關(guān)鍵詞：基于BP神經(jīng)網(wǎng)絡(luò)的個(gè)人信用風(fēng)險(xiǎn)評估模型的研究　出處：《太原理工大學(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)評估 評估指標(biāo)體系 BP神經(jīng)網(wǎng)絡(luò) 混合蛙跳算法

【摘要】：隨著經(jīng)濟(jì)社會(huì)的發(fā)展進(jìn)步,我國也逐漸向“信用經(jīng)濟(jì)”方向邁進(jìn)。加之我國經(jīng)濟(jì)政策的優(yōu)化調(diào)整,信貸業(yè)務(wù)已逐漸在我國的金融市場上遍地開花。隨著城市化建設(shè)步伐的加快,更加推動(dòng)了“房貸”、“車貸”等個(gè)人信貸業(yè)務(wù)的井噴式發(fā)展。但畢竟我國的信用體系建設(shè)起步晚、基礎(chǔ)差、經(jīng)驗(yàn)少,在實(shí)際應(yīng)用中難免有不足之處,尤其在“信用風(fēng)險(xiǎn)”控制方面常常顧此失彼。通過深入研究調(diào)研發(fā)現(xiàn),目前我國大多數(shù)銀行在進(jìn)行個(gè)人信用風(fēng)險(xiǎn)評估時(shí),普遍采用打分制的評估方法,且業(yè)務(wù)開辦實(shí)施多年來,評估指標(biāo)卻未能與時(shí)俱進(jìn),基本上沒有較大的改動(dòng)。顯然這種評估方式帶有很強(qiáng)的主觀性,評估指標(biāo)也相對落后,略顯刻板、單一。對此,本文提出了新的評估指標(biāo)體系,并采用改進(jìn)的BP算法建立了個(gè)人信用風(fēng)險(xiǎn)評估模型,希望能對銀行的個(gè)人信貸業(yè)務(wù)提供積極的參考意義。基于BP神經(jīng)網(wǎng)絡(luò)的個(gè)人信用風(fēng)險(xiǎn)評估模型的研究,本質(zhì)上需要解決三個(gè)問題:BP神經(jīng)網(wǎng)絡(luò)算法的改進(jìn)、個(gè)人信用風(fēng)險(xiǎn)評估指標(biāo)體系的建立及評估模型的構(gòu)建:(1)BP神經(jīng)網(wǎng)絡(luò)算法的改進(jìn):BP神經(jīng)網(wǎng)絡(luò)受初始權(quán)值和閾值的約束,容易陷入局部極小值點(diǎn)。而混合蛙跳算法是一種仿生智能優(yōu)化算法,具有良好的全局搜索能力,所以本文提出了用改進(jìn)的混合蛙跳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的解決辦法。(2)個(gè)人信用風(fēng)險(xiǎn)評估指標(biāo)體系的建立:在符合我國信用體系的實(shí)際發(fā)展背景下,本文主要參考借鑒了建設(shè)銀行個(gè)人信用評級、螞蟻金融芝麻信用、人人貸、美國FICO這四種個(gè)人信用評估方法的評估指標(biāo),以及中國人民銀行征信中心出具的個(gè)人征信報(bào)告。然后在傳統(tǒng)評估指標(biāo)的基礎(chǔ)上,剔除了一些對個(gè)人信用識別能力較差的指標(biāo)項(xiàng),添加了2項(xiàng)對個(gè)人信用評估有較強(qiáng)識別能力的“互聯(lián)網(wǎng)線上”指標(biāo)項(xiàng),打破了以往傳統(tǒng)評估指標(biāo)僅僅局限于“線下”的桎梏,做到了對借款人實(shí)施“線上+線下”的全方位評估。(3)評估模型的構(gòu)建:利用改進(jìn)后的混合蛙跳算法來優(yōu)化BP神經(jīng)網(wǎng)絡(luò)進(jìn)行模型建立,對“線上+線下”的18項(xiàng)指標(biāo)進(jìn)行科學(xué)的預(yù)測分析,實(shí)現(xiàn)對個(gè)人信用風(fēng)險(xiǎn)等級的評估,從而規(guī)避了傳統(tǒng)評估方法的主觀性,縮短了評估流程,提升了評估效率。最后通過實(shí)驗(yàn)論證模型的預(yù)測準(zhǔn)確率。
[Abstract]:With the development and progress of economy and society, our country is also gradually moving towards the direction of "credit economy", in addition to the optimization and adjustment of our country's economic policy. Credit business has gradually blossomed in China's financial market. With the acceleration of the pace of urbanization, the promotion of "housing loans". "car loan" and other personal credit business blowout development. But after all, the construction of credit system in China started late, the foundation is poor, the experience is less, it is inevitable to have deficiencies in the practical application. Especially in the control of "credit risk", we often lose sight of each other. Through in-depth research, it is found that most banks in our country generally use the evaluation method of scoring system when carrying out personal credit risk assessment. And the business implementation for many years, the evaluation index has failed to keep pace with the times, basically no major changes. Obviously, this evaluation method has a strong subjectivity, evaluation indicators are relatively backward, slightly rigid. Single. In this paper, a new evaluation index system is proposed, and an improved BP algorithm is used to establish a personal credit risk assessment model. The research of personal credit risk assessment model based on BP neural network, in essence, need to solve three problems: the improvement of BP neural network algorithm. The Establishment of personal Credit risk Evaluation Index system and the Establishment of Evaluation Model the improvement of the BP neural network algorithm is restricted by the initial weight and threshold. The hybrid leapfrog algorithm is a bionic intelligent optimization algorithm with good global search ability. Therefore, this paper proposes an improved hybrid leapfrog algorithm to optimize the BP neural network solution. 2) the establishment of personal credit risk evaluation index system: in line with the actual development of our country's credit system background. This paper mainly refers to the construction bank personal credit rating, ant finance Sesame credit, peer-to-peer lending, the United States FICO these four personal credit evaluation methods evaluation indicators. And the personal credit report issued by the credit information center of the people's Bank of China. Then on the basis of the traditional evaluation index, some index items with poor personal credit recognition ability are eliminated. This paper adds two "Internet online" indicators which have a strong ability to identify personal credit evaluation, which breaks the shackles of traditional evaluation indicators that are limited to "offline" only. The comprehensive evaluation model of "line up and below line" is constructed: the improved hybrid leapfrog algorithm is used to optimize the BP neural network to build the model. This paper carries on the scientific forecast and analysis to the "on-line and offline" 18 indexes, realizes the evaluation of personal credit risk grade, thus avoids the subjectivity of the traditional evaluation method and shortens the evaluation process. The evaluation efficiency is improved. Finally, the prediction accuracy of the model is proved by experiments.
【學(xué)位授予單位】：太原理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：F832.4;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 于曉陽;;互聯(lián)網(wǎng)+大數(shù)據(jù)模式下的征信——以芝麻信用為例[J];北方金融;2016年11期

2 葉文輝;;大數(shù)據(jù)征信機(jī)構(gòu)的運(yùn)作模式及監(jiān)管對策——以阿里巴巴芝麻信用為例[J];武漢金融;2016年02期

3 劉萬軍;楊笑;曲海成;;基于SQP局部搜索的蝙蝠優(yōu)化算法[J];計(jì)算機(jī)工程與應(yīng)用;2016年15期

4 劉新海;丁偉;;美國ZestFinance公司大數(shù)據(jù)征信實(shí)踐[J];征信;2015年08期

5 肖肖;駱建文;;基于大數(shù)據(jù)的互聯(lián)網(wǎng)融資平臺(tái)信用評級[J];現(xiàn)代管理科學(xué);2015年01期

6 朱榮恩;丁豪j;郭繼豐;;基于主體信用評級的中國社會(huì)信用體系建設(shè)——兼論中國信用評級業(yè)的發(fā)展戰(zhàn)略[J];征信;2014年12期

7 張蕾;;基于云計(jì)算的大數(shù)據(jù)處理技術(shù)[J];信息系統(tǒng)工程;2014年04期

8 王會(huì)娟;廖理;;中國P2P網(wǎng)絡(luò)借貸平臺(tái)信用認(rèn)證機(jī)制研究——來自“人人貸”的經(jīng)驗(yàn)證據(jù)[J];中國工業(yè)經(jīng)濟(jì);2014年04期

9 代永強(qiáng);王聯(lián)國;;PSO和SFLA混合優(yōu)化算法[J];計(jì)算機(jī)技術(shù)與發(fā)展;2014年04期

10 艾金娣;;P2P網(wǎng)絡(luò)借貸平臺(tái)風(fēng)險(xiǎn)防范[J];中國金融;2012年14期

相關(guān)博士學(xué)位論文 前1條

1 帥理;個(gè)人信用風(fēng)險(xiǎn)評估理論與方法的拓展研究[D];電子科技大學(xué);2015年

相關(guān)碩士學(xué)位論文 前2條

1 王丹;改進(jìn)混合蛙跳算法在云資源調(diào)度中的應(yīng)用[D];太原理工大學(xué);2016年

2 周蕾;粒子群算法的改進(jìn)及其在人工神經(jīng)網(wǎng)絡(luò)中的應(yīng)用[D];西安電子科技大學(xué);2010年

，

本文編號：1393069