商业银行非零售主标尺设计及优化研究

在商业银行内部评级体系中,建立非零售主标尺的目的在于区分不同类型客户的信用风险,进行违约概率区间划分。通过在违约概率和信用等级之间建立统一的对应关系,实现不同客户违约风险的比较,从而为实施差别化的风险管理奠定基础。主标尺设计不当,不仅会造成评级结果过于集中于某些特定的级别,而且容易造成部分或全部级别预测的违约概率大幅偏离实际违约率,监管资本计算失真以及经济资本错误分配等后果,直接影响风险预测的合理性。本文主要介绍主标尺构建的方法论、评估主标尺合理性的标准,探讨中国银行业在设计和优化主标尺过程中存在的问题及解决思路。     

非线性多重约束的内部评级违约概率模型的设计研究

2014年4月,经银监会核准,国内6家银行实施资本计量高级方法,其显著特色是过渡期后利用内部评级初级法下违约概率结果计量风险加权资产和监管资本。目前关于违约概率估计的研究大都存在未能严格遵循监管要求建立识别违约样本的标准,未能建立包括校准环节等在内的完整内部评级模型开发框架,以及未能将专家的业务经验纳入模型设计等方面的不足。鉴此,本文建立了一个满足监管合规要求的模型开发框架,设计了一个非线性多重约束的内部评级违约概率模型,并引入分类器原理评估模型的可靠性。基于某银行业务数据的实证研究表明,该模型效果良好。     

企业违约概率模型表现的监管标准研究

在内部评级法实施过程中,企业违约概率模型的表现是国内外监管机构持续关注的重点。企业违约概率模型表现的监管指标体系应以AR值(Accuracy Ratio,精确率)为区分力指标;以在一定的容忍度下,主标尺下各个级别的实际违约率围绕该级别违约概率中间值落入的设定区域为准确性指标和审慎性指标;以子样本AR值和不同时点上AR值的变化为稳定性指标。监管机构除了评估上述四个维度指标值的合理性以外,还需要结合银行主标尺设置、评级企业数量、违约企业数量、模型方法论等因素,整体判断企业违约概率模型的表现。     

我国商业银行中小企业贷款内部评级模型构建及实证研究

根据银监会最新文件要求,"银行内部评级应具备稳健的风险区分和排序能力,并准确量化风险"。本文从中小企业经营管理中的特有风险因素出发,在构建中小企业信用风险度量指标体系的基础上,采用符合巴塞尔协议内部评级法(IRB)要求的风险区分能力检验和稳健性检验的模型检验方法,构建具备稳健的风险区分和排序能力的信用评分模型。同时,针对评分模型完成校准过程,开发出符合银行实际情况和中小企业特殊情况的主标尺和映射函数,使评分模型的输出结果与"现实"的违约率(PD)以及评级结果形成较好的映射关系,并采用相关的检验方法对违约率的准确性进行验证,从而构建完整的具备稳健的风险区分和排序能力并能准确量化风险的内部评级模型。本研究对银行构建内部评级体系以及提高中小企业信用风险管理水平提供了实证的支持,具有一定现实参考意义。     

中小企业集合债券总体信用风险度量研究

中小企业集合债券总体信用风险既包括系统风险产生的周期性违约风险,又包括相互关联关系导致的传染性违约风险。首先通过对因素模型的改进构建模型Ⅰ,研究集合债券的周期性违约风险;在此基础上引入违约传染建立模型Ⅱ,分析违约传染对违约概率及违约相关性的影响,研究集合债券的总体信用风险。最后基于模型Ⅱ进行算例研究,得出结论：企业间的相互关联关系降低了其1次违约概率,增加了其多次违约概率即违约相关性。     

考虑违约风险的贷款组合管理

目前商业银行的主要业务还是集中在信贷业务,如何对贷款进行组合管理是银行所面临的问题。传统的马柯维茨均值——方差模型贷款组合模型,是以收益的方差作为风险度量指标,只考虑了市场风险,而没有考虑到企业的违约风险。本文用Merton模型根据企业财务数据估算出企业的预期违约概率,考虑了企业在违约情况下的收益率,把企业的违约概率纳入到组合模型中。用估算出来的违约概率和违约损失率计算出银行收益的波动性,再运用企业收益的相关性代替企业违约的相关性,根据现代组合分析模型得出收益-风险的有效前沿,从而使银行可以根据收益和风险承受能力对企业进行授信。     

如何利用CDS市场数据拟合不同存活率模型

信贷衍生工具评估的关键要素是违约时间模型。此类事件隐含的不确定性通过违约概率分布（也称为违约期限结构）模型获取,此模型对发行人在未来给定时间间隔内的违约概率进行建模。违约概率估算具有不同的类型：历史违约概率采用公司的信用等级转换或评分模型进行估算;结构模型综合市场以及资产负债表信息来计算违约概率;风险中性概率采用简化模型通过单纯的市场数据进行推导。     

生存分析、宏观经济变量与违约概率

在研究个人贷款违约风险中,传统的研究往往只单纯地将宏观经济指标作为协变量,并未考虑宏观经济指标的时变交互特征(vandell,1993;Zandi,1998)。国外研究达成共识的是以Logistic回归的传统模型不能给出违约概率的动态预测值,且反映经济形势的宏观经济变量也不能纳入模型中。论文论述了生存分析与Logistic模型的理论机理,试图在借贷违约风险中加入系统性风险对违约的影响因素,克服了以Logistic回归模型为代表的传统模型在度量信贷违约概率时仅考虑个体非系统性风险的局限。研究结论说明宏观经济变量确实对违约风险有影响,对网贷违约风险来说,Cox模型更优于Logistic函数。     

我国银行业信用风险宏观压力测试研究

本文通过实证研究提出并论证了一种宏观压力测试方法,该方法可用于银行业监管和系统性风险的防范.首先采用有序多分类Logistic模型测算行业原始违约概率,再运用MFD违约概率模型将宏观冲击因子引入以求得渗入宏观经济因子的违约概率,然后采用CreditRisk+模型分别测算不同宏观压力情景下与信用风险对应的经济资本变化,经...     

基于商业银行内部数据的KMV模型实证研究

本文借助KMV模型框架,对商业银行拥有的大量公司财务报表数据运用统计方法进行模型参数估计,计算得到了非上市公司的违约距离和经验函数,实现了违约概率的模型估计。实证表明,我国公司在违约距离或违约数量上的真实概率分布均呈现显著的T分布和肥尾特性;违约距离具有较高的风险区分能力;由会计信息进行参数估计的模型导出的具有较高的风险标志精度;进而表明基于会计报表数据的违约风险模型和基于资本市场数据的模型在实证上的有效性非常近似。     

Fast simulations in credit risk

We consider the problem of simulating tail loss probabilities and expected losses conditioned on exceeding a large threshold (expected shortfall) for credit portfolios. Our new idea, called the geometric shortcut, allows an efficient simulation for the case of independent obligors. It is even possible to show that, when the average default probability tends to zero, its asymptotic efficiency is higher than that of the naive algorithm. The geometric shortcut is also useful for models with dependent obligors and can be used for dependence structures modeled with arbitrary copulae. The paper contains the details for simulating the risk of the normal copula credit risk model by combining outer importance sampling with the geometric shortcut. Numerical results show that the new method is efficient in assessing tail loss probabilities and expected shortfall for credit risk portfolios. The new method outperforms all known methods, especially for credit portfolios consisting of weakly correlated obligors and for evaluating the tail loss probabilities at many thresholds in a single simulation run.     

Tracking bond indices in an integrated market and credit risk environment

Abstract

The management of credit risky assets requires simulation models that integrate the disparate sources of credit and market risk, and suitable optimization models for scenario analysis. In this paper we integrate Monte Carlo simulation models for credit risk with scenario optimization, and develop a methodology for tracking broadly defined corporate bond indices. Testing of the models shows that the integration of the multiple risk factors improves significantly the performance of tracking models. Good tracking performance can be achieved by optimizing strategic asset allocation among broad classes of corporate bonds. However, extra value is generated with a tactical model that optimizes bond picking decisions as well. It is also shown that adding small corporate bond holdings in portfolios that track government bond indices improves the risk/return characteristics of the portfolios. The empirical results to substantiate the findings of this study are obtained by backtesting the model over a recent 30 month period.     

Modeling of Contagious Credit Events and Risk Analysis of Credit Portfolios

We present a new model of the occurence of credit events such as rating changes and defaults for risk analyses of some portfolio credit derivatives. The framework of our model is based on a so-called top-down approach. Specifically, we first consider modeling the point process of each type of credit event in the whole economy using a self-exciting intensity process. Next, we characterize the point processes of credit events in the underlying sub-portfolio using random thinning processes specified by the distribution of credit ratings in the sub-portfolio. One of the main features of our model is that the model can capture credit risk contagion simultaneously among several credit portfolios. We present a credit event simulation algorithm based on our model and illustrate an application of the model to risk analyses of loan portfolios.     

Credit Portfolio Loss Forecasts for Economic Downturns

Recent studies find a positive correlation between default and loss given default rates of credit portfolios. In response, financial regulators require financial institutions to base their capital on 'Downturn' loss rates given default which are also known as Downturn LGDs. This article proposes a concept for the Downturn LGD which incorporates econometric properties of credit risk as well as the information content of default and loss given default models. The concept is compared to an alternative proposal by the Department of the Treasury, the Federal Reserve System and the Federal Insurance Corporation. An empirical analysis is provided for US American corporate bond portfolios of different credit quality, seniority and security.     

Law of large numbers and large deviations for dependent risks

We analyse the mathematical structure of models for large risk portfolios, especially for credit risk models. These risk portfolios are modelled using a multivariate mixture model for the dependence structure between the risks. The dependence structures are characterized by latent variables Θ, which play the role of systematic risks. We show that, depending on the choice of the distribution of Θ, there are different asymptotic behaviours for the aggregated risk portfolio, namely law of large numbers/central limit theorem behaviour and large deviation behaviour.     

Tempered stable structural model in pricing credit spread and credit default swap

In this paper, we explore the features of a structural credit risk model wherein the firm value is driven by normal tempered stable (NTS) process belonging to the larger class of Lévy processes. For the purpose of comparability, the calibration to the term structure of a corporate bond credit spread is conducted under both NTS structural model and Merton structural model. We find that NTS structural model provides better fit for all credit ratings than Merton structural model. However, it is noticed that probabilities of default derived from the calibration of the term structure of a bond credit spread might be overestimated since the bond credit spread could contain non-default components such as illiquidity risk or asymmetric tax treatment. Hence, considering CDS spread as a reflection of the pure credit risk for the reference entity, we calibrate it in order to obtain more reasonable probability of default and obtain valid results in calibration of the market CDS spread with NTS structural model.     

An analytic approach to credit risk of large corporate bond and loan portfolios

We derive an analytic approximation to the credit loss distribution of large portfolios by letting the number of exposures tend to infinity. Defaults and rating migrations for individual exposures are driven by a factor model in order to capture co-movements in changing credit quality. The limiting credit loss distribution obeys the empirical stylized facts of skewness and heavy tails. We show how portfolio features like the degree of systematic risk, credit quality and term to maturity affect the distributional shape of portfolio credit losses. Using empirical data, it appears that the Basle 8% rule corresponds to quantiles with confidence levels exceeding 98%. The limit law's relevance for credit risk management is investigated further by checking its applicability to portfolios with a finite number of exposures. Relatively homogeneous portfolios of 300 exposures can be well approximated by the limit law. A minimum of 800 exposures is required if portfolios are relatively heterogeneous. Realistic loan portfolios often contain thousands of exposures implying that our analytic approach can be a fast and accurate alternative to the standard Monte-Carlo simulation techniques adopted in much of the literature.     

Credit Risk Versus Capital Requirements under Basel II: Are SME Loans and Retail Credit Really Different?

Under Basel II, retail and SME credit (R&SME) receive special treatment because of a supposedly smaller exposure to systemic risk. Most research on this issue has been based on parameterized credit risk models. We present new evidence by applying Carey's (Carey, Mark. “Credit Risk in Private Debt Portfolios.” Journal of Finance 53, no. 4 (1998), 1363–1387.) nonparametric Monte-Carlo resampling method to two banks' complete loan portfolios. By exploiting that a sub-sample of all borrowers has been assigned an internal rating by both banks, we can compare the credit loss distributions for the three credit types, and compute both economic and regulatory capital under Basel II. We also test if our conclusions are sensitive to the definitions of R&SME credit. Our findings show that R&SME portfolios are usually riskier than corporate credit. Special treatment under Basel II is thus not justified. JEL classification: C14, C15, G21, G28, G33.     

Modelling default contagion using multivariate phase-type distributions

We model dynamic credit portfolio dependence by using default contagion in an intensity-based framework. Two different portfolios (with ten obligors), one in the European auto sector, the other in the European financial sector, are calibrated against their market CDS spreads and the corresponding CDS-correlations. After the calibration, which are perfect for the banking portfolio, and good for the auto case, we study several quantities of importance in active credit portfolio management. For example, implied multivariate default and survival distributions, multivariate conditional survival distributions, implied default correlations, expected default times and expected ordered default times. The default contagion is modelled by letting individual intensities jump when other defaults occur, but be constant between defaults. This model is translated into a Markov jump process, a so called multivariate phase-type distribution, which represents the default status in the credit portfolio. Matrix-analytic methods are then used to derive expressions for the quantities studied in the calibrated portfolios.     

Capital Allocation for Portfolio Credit Risk

Capital allocation rules are derived that maximize leverage while maintaining a target solvency rate for credit portfolios where risk is driven by a single common factor and idiosyncratic risk is fully diversified. Equilibrium conditions ensure that capital allocations depend on interest earnings as well as credits’ probability of default, endogenous loss given default, and asset correlation. Capitalization rates exceed those estimated using Gaussian credit loss models. Results demonstrate that credit risk is undercapitalized by the Basel II AIRB approach in part because of ambiguities regarding the definition of loss given default. An alternative proposed capital rule removes this bias.