Show simple item record

dc.contributor.advisor谢邦昌
dc.contributor.author吴见彬
dc.date.accessioned2016-02-14T03:28:00Z
dc.date.available2016-02-14T03:28:00Z
dc.date.issued2012-07-10 15:50:48.0
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/38409
dc.description.abstract近年来零售信贷业务发展迅猛,已经成为国内众多商业银行重点争夺的领域。与对公业务相比,零售业务呈现出客户量大但人均交易额小的特点,若使用人工逐户逐笔的方式进行审批和监管,不仅经营成本高业务效率低,还会出现人工评价标准不统一的问题。此外,银行零售市场具有信贷信息不对称的特征,这是信用风险产生的主要原因之一。在信贷信息不对称下,如何利用统计分析、数据挖掘等高新技术,建立可靠的分析模型,对用户的行为进行模型化自动化风险识别具有非常重要的意义。 本文首先剖析了随机森林的特征选择功能,指出随机森林计算出的变量重要性是有偏的,主要体现为:该重要性偏好于连续变量以及多类别的属性变量,同时还会受到输入变量间相...
dc.description.abstractThe retail credit business is developing rapidly in recent years and has become the key field of many domestic commercial banks. Compared with the public business, retail business has much more customers but smaller amount per customer. In this case, using manual audit, not only leads to high operating costs and low efficiency, but also causes conflicting manual evaluation standards. In addition, ...
dc.language.isozh_CN
dc.relation.urihttps://catalog.xmu.edu.cn/opac/openlink.php?strText=32401&doctype=ALL&strSearchType=callno
dc.source.urihttps://etd.xmu.edu.cn/detail.asp?serial=36518
dc.subject信息不对称
dc.subject信用风险
dc.subject随机森林
dc.subject随机生存森林
dc.subjectCforest
dc.subjectInformation Asymmetry
dc.subjectCredit Risk
dc.subjectRandom Forests
dc.subjectRandom Survival Forests
dc.subjectCforest
dc.title信息不对称下的银行零售信用风险研究——基于非参数随机森林
dc.title.alternativeResearch of Credit Risk under Asymmetric Information based on Nonparametric Random Forests
dc.typethesis
dc.date.replied2012-05-22
dc.description.note学位:经济学硕士
dc.description.note院系专业:经济学院计划统计系_统计学
dc.description.note学号:15420091151696


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record