Logit回归模型算法在典当公司信用风险度量中的应用——以A公司为例
|
摘要
典当公司作为专门从事发放抵押、质押贷款,以现金货币借贷为主要服务业务并兼任从事抵押商品出售市场的中介组织,是一种非典型的金融机构。当前,典当公司在以互联网金融为代表的小额借贷市场严峻的竞争局面下,为借款人给出接近甚至超出抵押、质押物价值的额度的借款额度,并降低所收的息费率,以此保住自己的市场份额。但这些营销手段大大提高了典当公司所面临的信用风险,也使典当公司对信用风险施行有效的度量和监控的需求更为迫切。本文通过一家较为典型的典当公司(A公司)信用风险度量模型构建的案例,结合典当公司的业务特点、需求和具体案例公司的样本,建立了信用风险度量的逻辑回归模型,并通过交叉验证和实践运用,得到了使用有效的评价。该研究结果可为提供借贷金融服务的典当行业,建立有效的信用风险度量方法提供一定的参考,模型选取的参数可为提供第三方征信服务的公司提供借鉴。
Pawnbroking company, as an intermediary organization specializing in the issuance of mortgage and pledge loans, with cash and currency lending as its main businesses and engaging in the selling of mortgaged goods, is not a typical financial institution.In this paper we combined the pawn company's business characteristics and needs of the specific case, and used the logistic regression to establish the credit risk measurement model. The model established passed the cross-validation and obtained the effective evaluation from users in the pawn company. The results of this study may provide some implications for the pawn industry to develop an effective credit risk measurement models and the parameters of the model may also provide some reference for the third party credit service companies.
Pawnbroking company, as an intermediary organization specializing in the issuance of mortgage and pledge loans, with cash and currency lending as its main businesses and engaging in the selling of mortgaged goods, is not a typical financial institution.In this paper we combined the pawn company's business characteristics and needs of the specific case, and used the logistic regression to establish the credit risk measurement model. The model established passed the cross-validation and obtained the effective evaluation from users in the pawn company. The results of this study may provide some implications for the pawn industry to develop an effective credit risk measurement models and the parameters of the model may also provide some reference for the third party credit service companies.
引文
[1]蔡文学,罗永豪,张冠湘等.基于GBDT与Logistic回归融合的个人信贷风险评估模型及实证分析.管理现代化,2017(3702):1-4.
[2]方匡南,吴见彬,朱建平等.信贷信息不对称下的信用卡信用风险研究.经济研究,2010(45S1):97-107.
[3]刘建和,王干,赵欣欣.典当行业现状及反思--基于浙江省典当行业的问卷调查分析.浙江金融,2017(03):67-73.
[4]柳向东,李凤.大数据背景下网络借贷的信用风险评估--以人人贷为例.统计与信息论坛,2016(3105):41-48.
[5]吕文栋,肖杨,赵杨.小额贷款公司中小企业法人客户信用风险评估研究.科学决策,2012(08):17-46.
[6]施锡铨,邹新月.典型判别分析在企业信用风险评估中的应用.财经研究,2001(10):53-57.
[7]王春峰,万海晖,张维.商业银行信用风险评估及其实证研究.管理科学学报,1998(01):70-74.
[8]吴建民,贾知青.K M V模型的信用风险度量特征.统计与决策,2004(11):122-123.参考文献
[9]杨晓晨.在产业升级与创新背景下的地炼企业信用风险特征研究.中外能源,2017(2205):81-87.
[10]张亮,张玲玲,陈懿冰等.基于信息融合的数据挖掘方法在公司财务预警中的应用.中国管理科学,2015(2310):170-176.
[11]张玲,曾维火.基于Z值模型的我国上市公司信用评级研究.财经研究,2004(06):5-13.
[12]Altman EI,G.MARCOG,VARETTO F.Corporate distress diagnosis:comparisons using linear discriminate analysis and neural networks.Journal of Banking and Finance,1994(18):505-529.
[13]AHNBA,CHO SS,KIM CY.The integrated methodology of rough set Theory and artificial neural network for business failure prediction.Expert Systems with Applications,2008,18(2):65-74.
[14]Engelmann B,Hayden E.,Tasche D.:TestingRatingAccuracy.Risk Magazine,January 2003,82-86.
[15]Gordy M.B.A comparative anatomy of credit risk models.Journal of Banking and Finance,2000,24(1-2):119-149.
[16]Moody’s Analytics,Inc.Risk Calc Pus Fact Sheet.New York.2013.l
[17]Ohlson JA.Financial Ratios and the Probabilistic Prediction of Bankruptcy.Journal of Operation Research,1980,9(15):109-131.
[2]方匡南,吴见彬,朱建平等.信贷信息不对称下的信用卡信用风险研究.经济研究,2010(45S1):97-107.
[3]刘建和,王干,赵欣欣.典当行业现状及反思--基于浙江省典当行业的问卷调查分析.浙江金融,2017(03):67-73.
[4]柳向东,李凤.大数据背景下网络借贷的信用风险评估--以人人贷为例.统计与信息论坛,2016(3105):41-48.
[5]吕文栋,肖杨,赵杨.小额贷款公司中小企业法人客户信用风险评估研究.科学决策,2012(08):17-46.
[6]施锡铨,邹新月.典型判别分析在企业信用风险评估中的应用.财经研究,2001(10):53-57.
[7]王春峰,万海晖,张维.商业银行信用风险评估及其实证研究.管理科学学报,1998(01):70-74.
[8]吴建民,贾知青.K M V模型的信用风险度量特征.统计与决策,2004(11):122-123.参考文献
[9]杨晓晨.在产业升级与创新背景下的地炼企业信用风险特征研究.中外能源,2017(2205):81-87.
[10]张亮,张玲玲,陈懿冰等.基于信息融合的数据挖掘方法在公司财务预警中的应用.中国管理科学,2015(2310):170-176.
[11]张玲,曾维火.基于Z值模型的我国上市公司信用评级研究.财经研究,2004(06):5-13.
[12]Altman EI,G.MARCOG,VARETTO F.Corporate distress diagnosis:comparisons using linear discriminate analysis and neural networks.Journal of Banking and Finance,1994(18):505-529.
[13]AHNBA,CHO SS,KIM CY.The integrated methodology of rough set Theory and artificial neural network for business failure prediction.Expert Systems with Applications,2008,18(2):65-74.
[14]Engelmann B,Hayden E.,Tasche D.:TestingRatingAccuracy.Risk Magazine,January 2003,82-86.
[15]Gordy M.B.A comparative anatomy of credit risk models.Journal of Banking and Finance,2000,24(1-2):119-149.
[16]Moody’s Analytics,Inc.Risk Calc Pus Fact Sheet.New York.2013.l
[17]Ohlson JA.Financial Ratios and the Probabilistic Prediction of Bankruptcy.Journal of Operation Research,1980,9(15):109-131.