宏观压力测试下商业银行零售信贷产品PD模型预测研究

通过将宏观经济指标与商业银行零售信贷产品住房按揭PD构建宏观变量预测模型，得到预测显著的GDP、CPI、HPI等三个宏观经济指标，再观察其不同滞后阶数组合VAR模型的AICC值，最终选取宏观经济因子高阶项构建回归方程和进行压力测试。研究结果发现：从施压时点开始，不同压力情景下PD均开始缓慢增长趋势，其中重度情景下PD增幅最大。说明使用宏观经济因子的阶乘能更好捕捉上述特征，PD预测模型能准确描述风险传导过程，此举可有效帮助商业银行加强零售信贷领域风险管理。     

CRMW风险缓释效用目标跟踪的债券投资组合优化策略研究

为缓释债券市场违约风险,央行着力推进信用风险缓释工具CRMW(信用风险缓释凭证)的发展,关于CRMW风险缓释能力度量及CRMW在债券投资组合中的应用成为了亟待解决的关键问题。为此,本文借鉴CVaR思想提出了“CRMW风险缓释效用”以度量CRMW对债券违约风险缓释能力,借助概率分位点理论定义债券的动态风险并制定了动态风险缓释跟踪目标,基于此跟踪目标探讨带有CRMW的债券投资组合优化策略问题。研究结果表明,在保证目标投资收益率的前提下,债券最优投资组合可达到风险缓释效用的目标,使其同时实现转移风险和保障收益的双重目的,且该投资组合优化策略表现出良好的抗风险性能。     

基于信用风险久期免疫的资产负债管理优化模型

用信用风险溢酬修正现金流的贴现率,构造了基于信用风险久期免疫条件;以组合收益最大为目标函数,建立了基于信用风险久期免疫的资产负债组合优化模型。本模型通过建立信用风险久期的免疫条件匹配银行的资产与负债,回避了利率风险和信用风险对银行所有者权益的影响;通过用反映违约风险的贴现率表述信用久期函数,揭示了信用风险对久期的影响;通过看跌期权公式建立了贴现率与违约风险的函数关系,揭示了违约风险对贴现率的影响。     

内生性回收率与信用风险度量研究

在信用风险模型中,外生性回收率的设定会忽略回收率对损失分布尾部的影响,而且会导致潜在的模型风险。本文将因子扩散过程引入结构信用风险模型,获得了回收率和违约概率之间的内在关系,利用Monte Carlo模拟方法数值分析了预期回收率对违约概率和资产价值波动率的依赖性,结果表明预期回收率与违约率之间具有很强的负相关关系,而且这种相关关系会受到债务人资产价值波动率的正向影响。在内生性回收率下,推导了信用损失的概率分布,计算了信用风险的Credit-VaR和ETF指标。最后利用市场数据检验了内生回收率信用风险模型的有效性,结果表明该模型可以很好的描述历史违约率和回收率的变化过程。     

厚尾分布情形下的信用资产组合风险度量

本文研究风险因子多元厚尾分布情形下的信用资产组合风险度量问题.用多元t-Copula分布来描述标的资产收益率分布的厚尾性,同时将三步重要抽样技术发展到基多元t-Copula分布的资产组合模型中,拓宽和丰富了信用资产组合风险度量模型.同时,并运用了非线性优化技术中的Levenberg-Marquardt算法来解决重要抽样技术中风险因子期望向量估计.模拟结果表明该算法比普通Monte Carlo模拟法的计算效率更有效,且能很大程度上减少所要估计的损失概率的方差,从而更精确地估计出信用投资组合损失分布的尾部概率或给定置信度下组合VaR值.     

违约风险下的信贷决策模型与机制

研究了违约风险下的信贷决策模型与机制,通过以银行个体合理性和激励相容性作为约束条件,建立了在考虑违约风险和项目成功概率条件下的信贷决策模型,分别给出了基于抵质押贷款和信用贷款策略下的信贷决策机制,探讨了信贷配给机制与无配给机制的设计方法,给出了在信贷出现配给时银行发放信用贷款和有抵质押贷款的条件.最后运用实例详细分析并讨论了不同违约概率条件下企业项目成功概率对银行期望收益的影响,得到了银行相应的贷款临界值和在不同项目成功概率条件下银行最大可接受的违约概率.     

Improving Default Risk Prediction Using Bayesian Model Uncertainty Techniques

Credit risk is the potential exposure of a creditor to an obligor's failure or refusal to repay the debt in principal or interest. The potential of exposure is measured in terms of probability of default. Many models have been developed to estimate credit risk, with rating agencies dating back to the 19th century. They provide their assessment of probability of default and transition probabilities of various firms in their annual reports. Regulatory capital requirements for credit risk outlined by the Basel Committee on Banking Supervision have made it essential for banks and financial institutions to develop sophisticated models in an attempt to measure credit risk with higher accuracy. The Bayesian framework proposed in this article uses the techniques developed in physical sciences and engineering for dealing with model uncertainty and expert accuracy to obtain improved estimates of credit risk and associated uncertainties. The approach uses estimates from one or more rating agencies and incorporates their historical accuracy (past performance data) in estimating future default risk and transition probabilities. Several examples demonstrate that the proposed methodology can assess default probability with accuracy exceeding the estimations of all the individual models. Moreover, the methodology accounts for potentially significant departures from “nominal predictions” due to “upsetting events” such as the 2008 global banking crisis.     

企业集团代理人风险态度、道德风险与信用风险传递

由于企业集团的关联企业众多,股权结构复杂,导致银企信息更加不对称,银行对企业集团贷款资金的监管更加困难,企业集团也更有机会产生不按照贷款合约使用贷款资金的道德风险,从而增大了银行的信用风险.针对此问题,首先分析了企业集团代理人转移银行贷款资金的动机,以及企业集团子公司之间信用风险的传递过程;其次,基于代理人效用最大化原理,分析委托代理合约、代理人风险态度,以及代理人转移贷款资金的道德风险对企业集团子公司信用风险的影响;最后,建立了度量企业集团子公司信用风险的违约概率模型.研究表明,代理人的风险态度、委托代理合约的状态都会影响企业集团子公司的违约概率.     

基于元胞自动机的企业集团信用风险传递仿真

 企业集团作为商业银行的重要客户,其内部信用风险传递机制的仿真与预测研究对于商业银行的风险控制尤其重要。而传统的仿真方法或者没有考虑到企业集团其本身的结构特性,或者过分依赖于具体随机过程的假定,大大降低了其结论的可靠性。因此,本文引入在生物与计算机领域广泛使用的元胞模型对企业集团内部关联信用风险传递机制进行仿真与模拟。研究发现,企业集团中的信用风险传递会出现风险分散和风险扩大两种不同的效应,并且母公司可以选择对各子公司的最优控制度使得母公司的违约概率最低。     

现代信用风险度量模型的实证比较与适用性分析

本文通过实证比较分析发现,现代信用风险度量模型对银行贷款的违约率、贷款损失和损失率的预测结果的差异性较大;但信用监测模型和信用风险附加法所预测的经济资本配置比例不仅符合巴塞尔协议对银行贷款经济资本的要求,也略大于实际应该配置的比例,实证表明了它们对度量我国商业银行贷款组合的信用风险具有较好的适用性.此外,本文也充分验证了借款人信用等级的不同,银行贷款经济资本配置的比例会有显著性的差异.     

零售信用组合的信用传染

利用复杂网络和流行过程理论,分析基于简单规则结构的信用传染、对均场依赖的信用传染以及信用传染中核心信用粒子与传染动态的关系.在简单规则网络的结构中,信用组合发生信用传染存在临界特征,当信用粒子被传染的概率高于临界值时,整个信用组合将被传染,信用网络发生的传染效应还受网络中节点状态、整个信用网络的均场状态等因素的影响.对均场依赖的信用传染中,信用传染存在对初始被传染密度、传染系数以及信用粒子恢复系数的依赖,并且传染过程也表现出依赖参数的临界特征.在信用传染中起核心传染作用的信用粒子,在整个组合演化中决定着非核心信用粒子被传染的规模.研究还发现信用传染过程对整个组合信用传染的均场依赖和对组合局部被传染密度的非线性依赖.研究为信用传染的压力测试提供理论支持.     

多银行贷款池的组合违约风险研究

资产组合的违约风险是决定其定价的重要因素.根据多银行贷款池这样一类特殊的资产组合的契约特征,可将其组合违约风险的影响因素分解为:1)宏观的系统风险因素;2)各贷款银行的风险因素;3)各债项的异质风险因素.在此基础上,构建了反映这类贷款池的违约风险和相关性结构的多因素模型,并在条件独立性假设和多元正态分布假设下,得到了该贷款池的违约行为随机特征.数值分析表明,多元正态分布的因素模型能够比较清楚地刻画所研究的多银行贷款池的组合违约风险.     

基于信用评分模型的我国商业银行客户违约概率研究

信用风险是商业银行面临的最主要和最复杂的风险。《巴塞尔新资本协议》对信用风险的计量提出了标准法和内部评级法,指出有条件的银行要实施内部评级法,通过对历史数据构建模型测算客户的违约概率。本文结合内部评级法和我国的实际情况,从客户评级的角度,研究了个人客户违约概率和公司客户违约概率。     

What factors drive personal loan fraud? Evidence from Germany

Based on a data set of nearly 43,000 personal loan applications from Germany, this paper empirically determines key factors of application fraud such as, for instance, the sales channel or the loan amount. This is done univariately as well as by employing a logistic regression, which is found to be a statistically significant approach for profiling loan application fraudsters. Besides in-sample and out-of-sample verifications, we also prove the economic significance of our results by developing a fraud management framework taking the fraud rate, the average default cost due to fraud as well as the fraud screening costs into account.     

CONSUMER CREDIT: EVIDENCE FROM ITALIAN MICRO DATA

In this paper we analyse unique data on credit applications received by the leading provider of consumer credit in Italy (Findomestic). The data set covers a five‐year period (1995–1999) during which the consumer credit market rapidly expanded in Italy and a new law (the usury law) came into force that set a limit on interest rates charged to consumers. We compute behavioural changes by controlling for changes in the observable characteristics of the Findomestic clientele and argue that, under suitable identifying assumptions, these changes can be given a structural interpretation. If the usury shock is assumed to have affected credit supply but not credit demand—that is, if the usury law had a differential impact on the supply of various types of credit but a uniform impact on demand—then we can identify and estimate a demand equation. Our key finding is that demand is interest‐rate elastic, particularly in the more affluent North. (JEL: D14, E21, G21)     

信贷市场主从微分对策模型与银行间合作机制研究

本文引入微分对策博弈模型,研究银行与企业之间的信贷博弈问题,破解企业融资困境。通过建立银行和企业的各自收益目标函数,讨论了银行区域内不合作和合作状况下,银行最优的动态信贷资金供应量和利率策略,企业动态信贷资金使用策略;研究了区域内银行间的合作联盟问题,提出合作联盟的利益共享。在银行区域内不合作情况下,银行信贷资金供应量增加,信贷资金利率上升趋势得到抑制,企业违规概率增加。利率和信贷资金供应量呈负相关关系。在银行区域合作情况下,银行间合作可防止企业囤积资金和贷款用途违规概率的上升,减少违规惩罚成本,促进企业积极履约。引入利益共享机制,解决了银行合作稳定问题,明确了优势企业和劣势企业的融资策略。     

信用风险的动态测量方法

本文提出了以市场波动性为基础的信用风险的一个动态量度框架.首先,通过把市场运动对信用暴露的影响量化,使得在信用风险的量度中融合了市场风险的因素,具有了动态的特征;其次,采用广义违约的概念,通过对基于历史数据的累计违约概率表进行拟合,得到了具有长期稳态的转移矩阵,由此得到的违约概率也具有动态属性;再次,根据有关金融产品优先级的历史数据,可以估计得到回收率;最后,把三者结合,得到了信用风险(信用损失)的动态量度,并对该量度框架的实际应用进行了探讨.     

A General Formula for Valuing Defaultable Securities

Previous research has shown that under a suitable no‐jump condition, the price of a defaultable security is equal to its risk‐neutral expected discounted cash flows if a modified discount rate is introduced to account for the possibility of default. Below, we generalize this result by demonstrating that one can always value defaultable claims using expected risk‐adjusted discounting provided that the expectation is taken under a slightly modified probability measure. This new probability measure puts zero probability on paths where default occurs prior to the maturity, and is thus only absolutely continuous with respect to the risk‐neutral probability measure. After establishing the general result and discussing its relation with the existing literature, we investigate several examples for which the no‐jump condition fails. Each example illustrates the power of our general formula by providing simple analytic solutions for the prices of defaultable securities.     

基于指标体系违约鉴别能力最大的小企业债信评级体系及实证

债信评级是通过评级体系确定债务违约的可能性大小。根据单个指标违约鉴别能力大小的遴选来建立评级指标体系看上去似乎是一个不错的选择，但事实并非如此。因为用违约鉴别能力强的单个指标组成的一组指标，其指标体系的违约鉴别能力却不一定强。本研究基于一组指标构成的指标体系的违约鉴别能力最大标准，构建了小企业债信评级体系。创新与特色：一是通过将单个违约鉴别力最强的指标组成的指标体系的b值，与本文建立的整体违约鉴别力最大的指标体系的b值对比，证明了单个违约鉴别力强的指标，组合起来的体系违约鉴别力不一定也强。在构建债信评级指标体系时，应关注指标体系整体的违约鉴别力，而非单个指标的违约鉴别力。二是在由n和n-1个指标构成的两组指标中，根据两组指标体系的非违约客户的综合得分S_i越高，则S_i偏离非违约状态（y_i=0）的距离越大；违约客户的综合得分S_i越低，S_i偏离违约状态（y_i=1）的距离越大；则布莱尔分数b越大，指标体系鉴别力越强的思路来遴选违约鉴别能力最大、而不是单个指标违约鉴别能力最大的一组指标体系，确保了评级体系具有最大的违约鉴别能力。三是在相关系数大于阈值的一对指标中，删除违约鉴别能力b值小、即区分违约状态能力弱的指标，既避免了指标体系的信息冗余、又避免了误删区分违约状态能力强的指标。实证表明：一是由于指标间的相互影响，单个违约鉴别力强的指标，组合起来的体系违约鉴别力不一定也强。二是非财务指标在小企业债信评级中的地位更加重要。     

External audit and bankruptcy prediction

In this paper, we investigate the relationship between external auditor characteristics and the likelihood of bankruptcy. We use a sample of US public companies to analyse whether auditor attributes are associated with default. We also test whether the inclusion of such attributes in bankruptcy prediction models improves their predictive ability. We find that firms audited by industry-expert auditors, large audit firms and long-tenured auditors are less likely to default. Firms with higher audit fees are more likely to default. Our results also show that the inclusion of auditor attributes significantly increases the predictive ability of bankruptcy prediction models. This paper contributes to the literature about auditing and bankruptcy prediction. Our results suggest that the auditor attributes can provide predictive signals concerning a default risk and that an external audit can play a relevant role in early warnings of financial distress. Our study also suggests that bankruptcy prediction models can become more effective if they are complemented with audit data. Our results are of interest to market participants, auditors, regulating authorities, banks and other financial institutions that are interested in credit risk assessment.