發(fā)布時(shí)間：2018-05-19 13:01

  本文選題：拒絕推論 + 貝葉斯界定折疊法��； 參考：《中南大學(xué)》2012年碩士論文

【摘要】：在小企業(yè)信用評分過程中經(jīng)常出現(xiàn)非隨機(jī)樣本選擇現(xiàn)象,該現(xiàn)象的產(chǎn)生是由于銀行信貸篩選過程中會(huì)導(dǎo)致一部分被拒絕企業(yè)的違約行為不能被觀測。數(shù)據(jù)缺失和樣本選擇性偏差可能導(dǎo)致模型參數(shù)估計(jì)有偏,從而對模型的預(yù)測能力產(chǎn)生較大影響。因此如何降低樣本有偏問題是研究信用評分模型的重要內(nèi)容之一。 根據(jù)大量文獻(xiàn)可以看出,一般的解決方法是拒絕推斷技術(shù)但大多數(shù)效果不甚理想。本文采用Sebasbiani口Ramoni (2000)基于貝葉斯理論提出的界定折疊法(Bound and Collapse, BC法),結(jié)合銀行信貸篩選過程,構(gòu)建出一種全新的拒絕推斷方法。該方法的原理是不論缺失數(shù)據(jù)機(jī)制如何,都可將缺失數(shù)據(jù)的參數(shù)估計(jì)通過某些極端分布限定在一定區(qū)間內(nèi)。區(qū)間的上下限由完全集內(nèi)的數(shù)據(jù)計(jì)算得出。而當(dāng)缺失數(shù)據(jù)的機(jī)制可知時(shí),區(qū)間內(nèi)的信息將由非響應(yīng)概率模型計(jì)算并最終獲得某個(gè)單值估計(jì)。BC法的第二步是將該區(qū)間坍塌成一個(gè)對于缺失數(shù)據(jù)的估計(jì)值。通過該方法,包含有樣本信息的數(shù)據(jù)將對缺失數(shù)據(jù)進(jìn)行填補(bǔ),從而獲得完整數(shù)據(jù)樣本為小企業(yè)信用評分模型的演化做準(zhǔn)備。 本文利用2003年美國小企業(yè)金融調(diào)研數(shù)據(jù)作為樣本,對模型的預(yù)測力和效果進(jìn)行檢驗(yàn)與評價(jià)。首先,對第一個(gè)子樣本做logistic回歸構(gòu)建信用評分模型,將該模型運(yùn)用到第二個(gè)子樣本,模擬銀行信貸篩選,并產(chǎn)生經(jīng)過信貸篩選后的選擇樣本。然后,基于有偏樣本構(gòu)建信用評分演化模型以驗(yàn)證其分類能力減弱甚至喪失的假設(shè)。最后,利用外部信息和內(nèi)部信息來估計(jì)缺失值,并對選擇樣本中的每一個(gè)缺失值進(jìn)行填補(bǔ)從而構(gòu)成完整樣本。 利用這種拒絕推斷技術(shù)的模型將與包含有全部數(shù)據(jù)的標(biāo)準(zhǔn)模型以及對缺失數(shù)據(jù)不做任何處理的審查模型進(jìn)行比較。為了檢驗(yàn)?zāi)Ｐ偷聂敯粜?本文設(shè)置兩種篩選率,不同的篩選率代表著樣本數(shù)據(jù)缺失程度不同和樣本選擇性偏差不同,并分別采用KS檢驗(yàn)、布萊爾評分、ROC曲線三種評估方法對模型進(jìn)行檢驗(yàn)。結(jié)果表明,貝葉斯界定折疊法在小企業(yè)信用評分演化模型中的應(yīng)用能有效提高模型分類能力,是在非隨機(jī)數(shù)據(jù)缺失機(jī)制下解決樣本偏差問題的有效途徑。
[Abstract]:Non-random sample selection often occurs in the credit scoring process of small enterprises, which is due to the fact that the default behavior of some rejected enterprises can not be observed during the process of bank credit screening. The lack of data and the deviation of sample selectivity may lead to biased estimation of model parameters, which has a great impact on the prediction ability of the model. Therefore, how to reduce sample bias is one of the important contents of credit scoring model. According to a large number of literatures, the general solution is rejection inference, but most of the results are not satisfactory. In this paper, Sebasbiani mouth Ramoni 2000) is used to construct a new method of refusal inference based on Bayesian theory, which is based on the defined folding method and bound and Collapse, BC method, combined with the process of bank credit screening. The principle of this method is that the parameter estimation of missing data can be limited to a certain range by some extreme distributions, regardless of the missing data mechanism. The upper and lower limits of the interval are calculated from the data in the complete set. When the mechanism of missing data is known, the information in the interval will be calculated by the non-response probability model and the second step of the single-valued estimation .BC method is to collapse the interval into an estimate of the missing data. Through this method, the missing data will be filled in by the data containing sample information, and the complete data sample will be obtained to prepare for the evolution of the credit scoring model of small enterprises. In this paper, the prediction force and effect of the model are tested and evaluated by using the financial survey data of American small enterprises in 2003 as a sample. First, the credit scoring model is constructed by logistic regression for the first sub-sample, and the model is applied to the second sub-sample to simulate the bank credit screening, and to produce the selected sample after the credit screening. Then, a credit score evolution model based on biased samples is constructed to verify the assumption that its classification ability is weakened or even lost. Finally, the missing value is estimated by external and internal information, and each missing value in the selected sample is filled to form a complete sample. The model using this rejection inference technique will be compared with the standard model that contains all the data and the review model that does not do any processing on the missing data. In order to test the robustness of the model, two screening rates are set up in this paper. The different screening rates represent different sample data missing degree and sample selectivity deviation, and KS test is used respectively. The model was tested by three evaluation methods: Blair score and ROC curve. The results show that the application of Bayesian defined folding method in the evolution model of small business credit scoring can effectively improve the classification ability of the model and is an effective way to solve the sample deviation problem under the mechanism of non-random data loss.
【學(xué)位授予單位】：中南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：F830.5;F224

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

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

2 程建;連玉君;劉奮軍;;信用風(fēng)險(xiǎn)模型的貝葉斯改進(jìn)研究[J];國際金融研究;2009年01期

3 楊暉;裴曦;;中小企業(yè)信用評分的應(yīng)用研究[J];廣西金融研究;2008年03期

4 吳德勝,梁梁;遺傳繁衍樣本策略及神經(jīng)網(wǎng)絡(luò)信用評價(jià)研究[J];管理科學(xué);2004年01期

5 肖進(jìn);賀昌政;;基于SODM的貝葉斯分類器結(jié)構(gòu)學(xué)習(xí)及其在客戶分類中的應(yīng)用[J];管理科學(xué);2008年04期

6 鄧超;敖宏;胡威;王翔;;基于關(guān)系型貸款的大銀行對小企業(yè)的貸款定價(jià)研究[J];經(jīng)濟(jì)研究;2010年02期

7 張文君;;小額信用貸款的風(fēng)險(xiǎn)管理:基于貝葉斯均衡的博弈分析[J];福建金融管理干部學(xué)院學(xué)報(bào);2011年01期

8 王學(xué)玲;;貝葉斯網(wǎng)絡(luò)分類模型研究及其在信用評估中的應(yīng)用[J];計(jì)算機(jī)與數(shù)字工程;2010年08期

9 李旭升;郭春香;陳凱亞;;最小總風(fēng)險(xiǎn)準(zhǔn)則的貝葉斯網(wǎng)絡(luò)個(gè)人信用評估模型[J];計(jì)算機(jī)應(yīng)用研究;2009年01期

10 傅鴻源;彭天明;;基于BP神經(jīng)網(wǎng)絡(luò)的建筑企業(yè)信用評價(jià)體系分析[J];科技管理研究;2008年11期

相關(guān)博士學(xué)位論文 前1條

1 丁東洋;信用風(fēng)險(xiǎn)分析中貝葉斯方法及其應(yīng)用研究[D];天津財(cái)經(jīng)大學(xué);2009年

，

本文編號(hào)：1910198