本文選題：信用評(píng)估 + 多元自適應(yīng)樣條回歸�。� 參考：《浙江工商大學(xué)》2012年碩士論文

【摘要】：信用卡對(duì)于個(gè)人、企業(yè)甚至國(guó)家的重要性不言而喻。目前,信用卡面臨的主要難題就是信用風(fēng)險(xiǎn),在普遍缺乏信用管理機(jī)制的中國(guó)該問(wèn)題顯得尤為突出。如何有效的控制風(fēng)險(xiǎn),最大化的取得收益,成為信用卡發(fā)布機(jī)構(gòu)面臨的一個(gè)重大難題。因此,從理論層面到實(shí)踐層面上,信用評(píng)估理論有了其廣闊的發(fā)揮空間。信用卡信用評(píng)估的目的在于利用現(xiàn)有的客戶屬性包括社會(huì)屬性和自然屬性將信用卡申請(qǐng)者分為兩類：對(duì)于能夠較好的履行還款義務(wù)的申請(qǐng)者劃分為“好客戶”,同意頒發(fā)信用卡。對(duì)于可能出現(xiàn)拖欠或拒絕還款的申請(qǐng)者劃分為“壞客戶”,拒絕通過(guò)信用卡申請(qǐng)。 早期的信用評(píng)估主要依賴于經(jīng)驗(yàn)式的定性分析,缺乏效率且極易受到操作人員的主觀影響。為此,眾多的專家學(xué)者試著設(shè)計(jì)合適的信用評(píng)估模型以用于定量的處理信用風(fēng)險(xiǎn)問(wèn)題。判別分析和logistic回歸是最常用的(參數(shù))統(tǒng)計(jì)分析方法。隨著計(jì)算機(jī)技術(shù)的發(fā)展,以數(shù)據(jù)驅(qū)動(dòng)作為核心思想的機(jī)器學(xué)習(xí)理論越來(lái)越受歡迎,決策樹、神經(jīng)網(wǎng)絡(luò)等在信用評(píng)估問(wèn)題中取得了較大的成功。 設(shè)計(jì)一個(gè)合適的信用評(píng)估模型是本文的主要研究?jī)?nèi)容,為此,文章首先介紹了信用評(píng)估模型的存在意義。其次在文獻(xiàn)綜述部分詳細(xì)的給出了建立信用評(píng)估模型的各個(gè)步驟以及目前的研究狀況。然后通過(guò)對(duì)常見信用模型的梳理指出了其存在的優(yōu)缺點(diǎn)。 最后本文提出了MARS-SVM模型,充分利用MARS全局處理變量,并能對(duì)變量重要性進(jìn)行排序的優(yōu)點(diǎn)彌補(bǔ)了SVM不能進(jìn)行特征選擇的缺陷,從而得到了具有較高預(yù)測(cè)能力的混合模型：MARS是現(xiàn)代回歸分析方法,對(duì)數(shù)據(jù)分布要求不高,通過(guò)逐步向前引入變量,逐步向后刪除不重要變量的方式建立回歸模型。所以MARS對(duì)變量的重要性排序具有全局最優(yōu)性。SVM利用格點(diǎn)搜索法并采用交叉驗(yàn)證的方式確定懲罰參數(shù)和核函數(shù)參數(shù)。因此雖然其算法特性避免了“維度災(zāi)難”,但是過(guò)多的預(yù)測(cè)變量會(huì)影響其工作效率,而MARS的變量篩選正是其合理的補(bǔ)充。SVM的核心部分是核函數(shù)的選擇,Rbf核函數(shù)具有普適性,易操作性的優(yōu)點(diǎn)最受歡迎。但同時(shí)Rbf可能會(huì)導(dǎo)致特征空間樣本信息損失所以在Rbf核函數(shù)基礎(chǔ)上提出了KOBF核函數(shù)。本文將同時(shí)使用KOBF和Rbf作為SVM的核函數(shù)以對(duì)比分類效果。 為了驗(yàn)證模型MARS-SVM的預(yù)測(cè)能力,本文做了對(duì)比實(shí)驗(yàn)。利用logistic回歸、分類決策樹、神經(jīng)網(wǎng)絡(luò)對(duì)同一樣本數(shù)據(jù)集做了分類處理。結(jié)果顯示,MARS-SVM模型具有較好的預(yù)測(cè)能力。
[Abstract]:The importance of credit cards to individuals, businesses and even the state is self-evident.At present, credit risk is the main problem faced by credit card, especially in China, where credit management mechanism is generally lacking.How to effectively control the risk and maximize the income has become a major problem faced by credit card issuers.Therefore, from the theoretical level to the practical level, the theory of credit evaluation has its broad scope.The purpose of credit card credit evaluation is to use existing customer attributes, including social attributes and natural attributes, to divide credit card applicants into two categories: those who are better able to meet their repayment obligations are classified as "good customers."Agree to issue a credit card.Applicants who may default or reject payments are classified as "bad customers" who reject credit card applications.The early credit evaluation mainly depends on the empirical qualitative analysis, which is inefficient and easily influenced by the operator.Therefore, many experts and scholars try to design appropriate credit evaluation model to deal with credit risk quantitatively.Discriminant analysis and logistic regression are the most commonly used statistical analysis methods.With the development of computer technology, the theory of machine learning with data-driven as its core is becoming more and more popular. Decision tree and neural network have achieved great success in credit evaluation.Designing a suitable credit evaluation model is the main research content of this paper. Therefore, this paper first introduces the significance of the credit evaluation model.Secondly, in the part of literature review, the steps of establishing credit evaluation model and the current research situation are given in detail.Then, the advantages and disadvantages of the common credit models are pointed out.Finally, this paper proposes a MARS-SVM model, which makes full use of MARS to deal with variables globally, and can sort the importance of variables to make up for the defect that SVM can not select features.It is concluded that the hybrid model: Mars with high predictive ability is a modern regression analysis method with low requirement for data distribution. The regression model is established by introducing variables forward step by step and deleting unimportant variables step by step.Therefore, MARS has global optimality for the importance of variables. SVM uses lattice search method to determine the penalty parameters and kernel function parameters.Therefore, although its algorithm features avoid "dimensionality disaster", too many prediction variables will affect its work efficiency, and the selection of kernel function is the core part of MARS, which is a reasonable supplement to .SVM.The advantages of ease of operation are most popular.But at the same time, Rbf may lead to the loss of sample information in the feature space, so the KOBF kernel function is proposed based on the Rbf kernel function.In this paper, both KOBF and Rbf are used as kernel functions of SVM to compare classification effects.In order to verify the prediction ability of the model MARS-SVM, a comparative experiment is made in this paper.Logistic regression, classification decision tree and neural network are used to classify the same sample data set.The results show that the MARS-SVM model has better prediction ability.
【學(xué)位授予單位】：浙江工商大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：F832.2;F224

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 姜明輝,王歡,王雅林;分類樹在個(gè)人信用評(píng)估中的應(yīng)用[J];商業(yè)研究;2003年21期

2 郭振亞;;支持向量機(jī)在信用卡信用評(píng)估的應(yīng)用[J];電腦知識(shí)與技術(shù);2009年07期

3 李建平,徐偉宣,石勇;基于主成分線性加權(quán)綜合評(píng)價(jià)的信用評(píng)分方法及應(yīng)用[J];系統(tǒng)工程;2004年08期

4 王莉莉;曹敢;石亮;王東升;;一種基于Logistic回歸和分類樹的客戶信用評(píng)估方法研究[J];江蘇科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年S1期

5 向暉;楊勝剛;;基于多分類器組合的個(gè)人信用評(píng)估模型[J];湖南大學(xué)學(xué)報(bào)(社會(huì)科學(xué)版);2011年03期

6 姜明輝;謝行恒;王樹林;溫瀟;;個(gè)人信用評(píng)估的Logistic-RBF組合模型[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2007年07期

7 龐素琳;王燕鳴;;判別分析模型在信用評(píng)價(jià)中的應(yīng)用[J];南方經(jīng)濟(jì);2006年03期

8 石慶焱,靳云匯;個(gè)人信用評(píng)分的主要模型與方法綜述[J];統(tǒng)計(jì)研究;2003年08期

9 石慶焱,靳云匯;多種個(gè)人信用評(píng)分模型在中國(guó)應(yīng)用的比較研究[J];統(tǒng)計(jì)研究;2004年06期

10 李貴洋;郭濤;劉芳;;基于支持向量機(jī)的信用卡欺詐檢測(cè)[J];微計(jì)算機(jī)信息;2010年06期

相關(guān)博士學(xué)位論文 前1條

1 沈翠華;基于支持向量機(jī)的消費(fèi)信貸中個(gè)人信用評(píng)估方法研究[D];中國(guó)農(nóng)業(yè)大學(xué);2005年

相關(guān)碩士學(xué)位論文 前2條

1 霍明;短期負(fù)荷預(yù)測(cè)的支持向量機(jī)模型參數(shù)優(yōu)化方法研究[D];湖南大學(xué);2009年

2 劉志燾;基于支持向量機(jī)的不常用備件分類模型研究[D];華中科技大學(xué);2008年

，

本文編號(hào)：1754173