本文選題：信用評(píng)分 + 樣本偏差��； 參考：《哈爾濱工業(yè)大學(xué)》2014年碩士論文

【摘要】：隨著商業(yè)銀行的快速發(fā)展，信貸業(yè)務(wù)在其發(fā)展進(jìn)程中的地位日益顯著，信貸風(fēng)險(xiǎn)水平的控制直接影響到商業(yè)銀行整體的進(jìn)展。因此，對(duì)個(gè)人信貸風(fēng)險(xiǎn)的識(shí)別和評(píng)估的準(zhǔn)確與否，就成為了商業(yè)銀行能否合理控制風(fēng)險(xiǎn)的至關(guān)因素。過(guò)去的研究主要集中在模型精度的提高對(duì)評(píng)分方法進(jìn)行挖掘及優(yōu)化，而忽略了“拒絕推論”即樣本偏差這一重要問(wèn)題。由于很多評(píng)分機(jī)構(gòu)只能將接受樣本的部分?jǐn)?shù)據(jù)通過(guò)信用模型來(lái)預(yù)測(cè)貸款申請(qǐng)者違約與否，導(dǎo)致出現(xiàn)樣本偏差問(wèn)題進(jìn)而影響信用評(píng)分模型的有效性。因此，在信用評(píng)估范疇內(nèi)，樣本偏差問(wèn)題是一個(gè)急需處理的問(wèn)題。 本文首先對(duì)樣本偏差及其糾正技術(shù)進(jìn)行了分析。提出了利用蒙特卡洛生成隨機(jī)數(shù)的方法產(chǎn)生樣本，加入到原始樣本中形成新樣本集從而優(yōu)化樣本集，利用加入生成樣本后的優(yōu)化樣本集來(lái)解決樣本偏差這一問(wèn)題。在產(chǎn)生樣本方面，本文對(duì)生成樣本的生成方法進(jìn)行了闡述及選擇，并對(duì)個(gè)人信用評(píng)分指標(biāo)體系進(jìn)行構(gòu)建，確定商業(yè)銀行個(gè)人信用評(píng)分指標(biāo)，通過(guò)對(duì)商業(yè)銀行原始樣本的指標(biāo)進(jìn)行分析，確定其分布規(guī)律及內(nèi)在聯(lián)系，產(chǎn)生指標(biāo)數(shù)據(jù)，，同時(shí)對(duì)數(shù)據(jù)相應(yīng)的還款情況進(jìn)行分類，運(yùn)用軟件進(jìn)行訓(xùn)練形成生成樣本。并對(duì)生成樣本加入原始樣本中好壞客戶比例及生成樣本和原始樣本的搭配比例進(jìn)行了構(gòu)造及說(shuō)明，最終形成優(yōu)化樣本集。最后，利用優(yōu)化樣本集對(duì)評(píng)分領(lǐng)域單一模型和組合預(yù)測(cè)模型進(jìn)行了效果檢驗(yàn)。檢驗(yàn)結(jié)果表明，將優(yōu)化樣本集作為個(gè)人信用評(píng)分模型的樣本數(shù)據(jù)不僅能使其預(yù)判精度明顯提高，同時(shí)也能使得樣本偏差問(wèn)題得到很好的解決。
[Abstract]:With the rapid development of commercial banks, credit business is playing an increasingly important role in the development process. The control of credit risk level directly affects the overall progress of commercial banks. Therefore, the identification and evaluation of personal credit risk is the most important factor for commercial banks to reasonably control the risk. In the past, the research focused on improving the accuracy of the model to mine and optimize the scoring method, while ignoring the important problem of "reject inference", that is, sample deviation. Because many rating organizations can only use credit model to predict loan applicant default or not, the sample deviation problem will affect the validity of credit rating model. Therefore, sample deviation is an urgent problem in credit evaluation. In this paper, the sample deviation and its correction technique are analyzed. This paper presents a method of generating samples by using Monte Carlo to generate random numbers, which is added to the original samples to form a new sample set to optimize the sample set. The problem of sample deviation is solved by using the optimized sample set after adding the generated sample. In the aspect of producing samples, this paper expounds and selects the method of generating samples, and constructs the index system of personal credit score, and determines the index of personal credit score of commercial banks. Through the analysis of the index of the original sample of commercial bank, the distribution law and internal relation are determined, and the index data is produced. At the same time, the corresponding repayment situation of the data is classified, and the training software is used to form the generated sample. Finally, the optimal sample set is formed by constructing and illustrating the proportion of good or bad customers added to the original sample and the collocation ratio between the generated sample and the original sample. Finally, the single model and combined prediction model in scoring field are tested by the optimized sample set. The test results show that using the optimized sample set as the sample data of personal credit scoring model can not only improve the precision of prediction, but also solve the problem of sample deviation.
【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】：2014
【分類號(hào)】：F224;F830.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳元燮;建立信用評(píng)級(jí)指標(biāo)體系的幾個(gè)理論問(wèn)題[J];財(cái)經(jīng)問(wèn)題研究;2000年08期

2 石曉軍,肖遠(yuǎn)文,任若恩;Logistic違約率模型的最優(yōu)樣本配比與分界點(diǎn)研究[J];財(cái)經(jīng)研究;2005年09期

3 崔家銘;熊鈺君;;商業(yè)銀行個(gè)人信用指標(biāo)體系研究綜述[J];東方企業(yè)文化;2011年02期

4 楊紹基;范閩;;信用評(píng)分模型的拒絕偏差與Heckit糾正[J];南方金融;2007年05期

5 鄧超;胡威;唐瑩;;基于拒絕推論的小企業(yè)信用評(píng)分模型研究[J];國(guó)際金融研究;2011年04期

6 蘭硯軍;;基于AHP法高校學(xué)生信用指標(biāo)權(quán)重的確定[J];電大理工;2012年04期

7 ;Oxford University Press[J];分子植物育種;2007年02期

8 鄧云勝,沈沛龍,任若恩;貸款組合信用風(fēng)險(xiǎn)VaR的蒙特卡羅仿真[J];計(jì)算機(jī)仿真;2003年02期

9 方維;;基于蒙特卡洛模擬的項(xiàng)目風(fēng)險(xiǎn)管理方法研究[J];計(jì)算機(jī)與現(xiàn)代化;2012年04期

10 吳瑩輝;;基于BP神經(jīng)網(wǎng)絡(luò)模型的個(gè)人信用風(fēng)險(xiǎn)評(píng)估研究[J];科技創(chuàng)業(yè)月刊;2012年07期

本文編號(hào)：1791409