Haar wavelets-based approach for quantifying credit portfolio losses

This paper proposes a new methodology to compute Value at Risk (VaR) for quantifying losses in credit portfolios. We approximate the cumulative distribution of the loss function by a finite combination of Haar wavelet basis functions and calculate the coefficients of the approximation by inverting its Laplace transform. The Wavelet Approximation (WA) method is particularly suitable for non-smooth distributions, often arising in small or concentrated portfolios, when the hypothesis of the Basel II formulas are violated. To test the methodology we consider the Vasicek one-factor portfolio credit loss model as our model framework. WA is an accurate, robust and fast method, allowing the estimation of the VaR much more quickly than with a Monte Carlo (MC) method at the same level of accuracy and reliability.     

What influences banks’ choice of credit risk management practices? Theory and evidence

Banks use different risk management practices with varying levels of sophistication. This paper examines the factors that determine the choice of risk-management practices. In a theoretical model, we identify two main determinants for the choice of risk management tools: bank competition and sector concentration in the loan market. We empirically test the predictions of our model using hand-collected data on the credit risk management of 249 German savings banks. The results are in line with our theory: Competition pushes banks to implement advanced risk management practices. Sector concentration in the loan market promotes credit portfolio modeling, but it inhibits credit risk transfer.     

A mathematical model for multi-name credit based on community flocking

We present a new mathematical model for multi-name credit that employs stochastic flocking. Flocking mechanisms have been used in a variety of models of biological, sociological and physical aggregation phenomena. As a direct application of a flocking mechanism, we introduce a credit risk model based on community flocking for a credit worthiness index. Correlations between different credit worthiness indices are explained in terms of communication rates and coupling strengths from the flocking system. Based on the flocking model, we compute credit curves for individual names and default time distributions. We also apply the proposed model to the pricing of credit derivatives such as credit default swaps and collateralized debt obligations.     

Modeling loan commitments

Loan commitments represent more than 82 percent of all commercial and industrial loans by domestic banks. This paper develops a valuation model for loan commitments incorporating early exercise, multiple fees, partial exercise and credit risk. The model is analytically tractable and easy to implement. Using a sample of commercial paper backup credit lines from the Dealscan database, we show that our model prices closely match loan commitment market prices.     

A framework to measure integrated risk

A framework underlying various models that measure the credit risk of a portfolio is extended in this paper to allow the integration of credit risk with a range of market risks using Monte Carlo simulation. A structural model is proposed that allows interest rates to be stochastic and provides closed-form expressions for the market value of a firm's equity and its probability of default. This model is embedded within the integrated framework and the general approach illustrated by measuring the risk of a foreign exchange forward when there is a significant probability of default by the counterparty. For this example moving from a market risk calculation to an integrated risk calculation reduces the expected future value of the instrument by an amount that could not be calculated using the common pre-settlement exposure technique for estimating the credit risk of a derivative.     

基于多层次模糊综合评价的中小企业信用风险评估

引入多层次模糊评价方法,设计包括行业状况、上下游状况、产品状况、管理水平、财务状况和资信状况的指标体系,构建多层次模糊综合评价的中小企业信用风险评估模型。算例分析表明该方法综合了定性因素和定量因素,能有效地评价中小企业的信用风险。     

创新信用衍生工具 提升风险管理能力——巴塞尔协议Ⅲ背景下的CRM

最新公布的巴塞尔协议Ⅲ,要求银行业充分吸取金融危机教训,切实加强信用风险管理。中国银行间市场推出的信用风险缓释工具,具有多项创新价值,发挥了本土市场成功经验。从微观角度,该工具有助于提高信用风险动态管理能力、丰富资本管理手段、支持逆周期管理和灵活平衡集中度;从宏观角度,该工具有助于打造渐进式风险管理机制、强化资本约束并带动市场基础建设。为进一步推进中国信用衍生产品市场发展,建议发挥商业银行的主导作用和非银行机构的辅助作用,完善交易机制、定价机制和会计处理,创新清算机制,并纳入银行自身风险管理流程。     

Interpretable selective learning in credit risk

Forecasting credit default risk has been an important research field for several decades. Traditionally, logistic regression has been widely recognized as a solution because of its accuracy and interpretability. Although complex machine learning models may improve accuracy over simple logistic regressions, their interpretability has prevented their use in credit risk assessment. We introduce a neural network with a selective option to increase interpretability by distinguishing whether linear models can explain the dataset. Our methods are tested on two datasets: 25,000 samples from the Taiwan payment system collected in October 2005 and 250,000 samples from the 2011 Kaggle competition. We find that, for most of samples, logistic regression will be sufficient, with reasonable accuracy; meanwhile, for some specific data portions, a shallow neural network model leads to much better accuracy without significantly sacrificing interpretability.     

中小企业信用担保风险形成的内在机制研究

从信息经济学角度讨论了金融市场中的信息不对称理论,接着对信息不对称导致中小企业信用担保风险形成的内在机制进行了深入研究,并基于风险识别、风险预警、科学运营、风险内部分散、风险内部转移、风险内部补偿等分目标,构建了中小企业信用担保风险的内部控制机制的整体架构,为中小企业信用担保的科学化实践提供参考.     

A new mixture cure model under competing risks to score online consumer loans

In credit scoring, survival analysis models have been widely applied to answer the question as to whether and when an applicant would default. In this paper, we propose a novel mixture cure proportional hazards model under competing risks. Most existing mixture cure models either do not consider competing risks or generally assume that a subpopulation of subjects is immune to any risk from all the competing risks. Compared with existing models, the proposed model is more flexible since it assumes that a subpopulation of subjects is immune to a subset of risks instead of being immune to all the risks. To estimate model parameters, we derive the likelihood function of the proposed model, based on which an expectation maximization estimation algorithm is developed. A simulation algorithm is designed to simulate time-to-event observations from the proposed model, and simulation studies are conducted to verify the proposed methodology. A real world example of credit scoring for online customer loans based on the proposed model is demonstrated.     

Dynamic mean–VaR portfolio selection in continuous time

The value-at-risk (VaR) is one of the most well-known downside risk measures due to its intuitive meaning and wide spectra of applications in practice. In this paper, we investigate the dynamic mean–VaR portfolio selection formulation in continuous time, while the majority of the current literature on mean–VaR portfolio selection mainly focuses on its static versions. Our contributions are twofold, in both building up a tractable formulation and deriving the corresponding optimal portfolio policy. By imposing a limit funding level on the terminal wealth, we conquer the ill-posedness exhibited in the original dynamic mean–VaR portfolio formulation. To overcome the difficulties arising from the VaR constraint and no bankruptcy constraint, we have combined the martingale approach with the quantile optimization technique in our solution framework to derive the optimal portfolio policy. In particular, we have characterized the condition for the existence of the Lagrange multiplier. When the opportunity set of the market setting is deterministic, the portfolio policy becomes analytical. Furthermore, the limit funding level not only enables us to solve the dynamic mean–VaR portfolio selection problem, but also offers a flexibility to tame the aggressiveness of the portfolio policy.     

An application of data envelopment analysis to the evaluation of audit risk: a reinterpretation

This paper, which reinterprets previous work by Bradbury and Rouse (2002 ), addresses the risk quantification issue at an intuitive level. The insights provided by such quantification are discussed. Risk factors are associated with the risk-return concept. This allows measuring whether risks taken on are appropriately rewarded. The paper gives a non-technical exposition of DEA and outlines possible applications to accounting and finance. Using data for a large multinational, it shows how DEA analysis can be combined with internal audit procedures. It explains how the results obtained can be used to improve risk management.     

A study on risk retention regulation in asset securitization process

We study the impacts of the recently proposed risk retention regulation for asset securitization, i.e. the issuer has to retain a certain proportion of securitized assets. We also consider the frequently discussed measure to require the issuer disclose certain information of the securitized assets. In a dynamic model with asymmetric information between a risk-averse originating bank and a continuum of risk-averse investors, we find that it is impossible for a flat-rate retention requirement to be optimal for all asset types. Although both risk retention and information disclosure regulations are effective in reducing investors’ informational loss, neither can unconditionally enhance social welfare upon the unregulated case. For both measures, there are associated regulatory cost: risk retention regulation aggravates adverse selection problem because it undermines the channel of informational revelation by the choice of securitization intensity, and information disclosure requirement incurs a signalling cost by distorting banks’ securitization intensity in sending signals. Under an appropriate set of conditions we find that information disclosure requirement complements risk retention regulation when investors are sufficiently risk averse.     

The impact of the choice of VaR models on the level of regulatory capital according to Basel II

The Basel II framework allows the calculation of the capital requirements for market risk with Value-at-Risk models. Since no special model is prescribed in the framework, banks may use simple models with questionable assumptions concerning their underlying distributions. Our numerical analysis reveals that simple VaR models that perform noticeably worse than comparable simple models with more realistic assumptions may lead to a lower level of regulatory capital for banks. For this reason, banks have a major incentive to implement bad models. This is obviously contrary to the interests of regulatory authorities.     

The impact of enterprise risk management on the marginal cost of reducing risk: Evidence from the insurance industry

We test the hypothesis that practicing enterprise risk management (ERM) reduces firms’ cost of reducing risk. Adoption of ERM represents a radical paradigm shift from the traditional method of managing risks individually to managing risks collectively allowing ERM-adopting firms to better recognize natural hedges, prioritize hedging activities towards the risks that contribute most to the total risk of the firm, and optimize the evaluation and selection of available hedging instruments. We hypothesize that these advantages allow ERM-adopting firms to produce greater risk reduction per dollar spent. Our hypothesis further predicts that, after implementing ERM, firms experience profit maximizing incentives to lower risk. Consistent with this hypothesis, we find that firms adopting ERM experience a reduction in stock return volatility. We also find that the reduction in return volatility for ERM-adopting firms becomes stronger over time. Further, we find that operating profits per unit of risk (ROA/return volatility) increase post ERM adoption.     

A new approach to assessing model risk in high dimensions

A central problem for regulators and risk managers concerns the risk assessment of an aggregate portfolio defined as the sum of d individual dependent risks $X_i$. This problem is mainly a numerical issue once the joint distribution of $\left(X_1\text{,}{X}_2\text{,}\dots \text{,}{X}_d\right)$ is fully specified. Unfortunately, while the marginal distributions of the risks $X_i$ are often known, their interaction (dependence) is usually either unknown or only partially known, implying that any risk assessment of the portfolio is subject to model uncertainty.Previous academic research has focused on the maximum and minimum possible values of a given risk measure of the portfolio when only the marginal distributions are known. This approach leads to wide bounds, as all information on the dependence is ignored. In this paper, we integrate, in a natural way, available information on the multivariate dependence. We make use of the Rearrangement Algorithm (RA) of Embrechts et al. (2013) to provide bounds for the risk measure at hand. We observe that incorporating the information of a well-fitted multivariate model may, or may not, lead to much tighter bounds, a feature that also depends on the risk measure used. In particular, the risk of underestimating the Value-at-Risk at a very high confidence level (as used in Basel II) is typically significant, even if one knows the multivariate distribution almost completely.Our results make it possible to determine which risk measures can benefit from adding dependence information (i.e., leading to narrower bounds when used to assess portfolio risk) and, hence, to identify those situations for which it would be meaningful to develop accurate multivariate models.     

Alternative to beta coefficients in the context of diffusions

We develop an alternative to the beta coefficient of the CAPM theory. We show the link between this notion and the Wiener chaos expansion of the underlying processes. In the setting of Markov diffusions, we define the drift-neutral beta, which is the quantity of benchmark such that the resulting portfolio is immune to an infinitesimal change of drift on the Brownian motion driving the benchmark. Our approach yields a coefficient which in many practical cases depends on the initial values of both the portfolio and its benchmark. It can also be used to take into account extreme risks and not only the variance. We study several classical diffusion processes and give a full analysis in the case of Jacobi processes. Examples with credit indices show the efficiency of the method in hedging a portfolio.     

基于隐马尔可夫模型的物流企业客户违约风险评估

物流企业客户违约及其变化过程具有马尔可夫性。在利用经典算法预测违约损失值的基础上,将违约损失值作为影响因素,借鉴隐马尔可夫理论,构建基于影响因素的物流企业客户违约风险评估模型。通过该模型可以计算得到某一时刻物流企业服务的每个客户的违约风险及其风险变化指数和物流企业面临的平均违约风险及其变化指数。算例计算结果表明,该评估模型能够准确度量客户违约风险,并具有可行性和易操作性。     

典型事实、极值理论与金融市场动态风险测度研究

本文在金融市场典型事实约束下,运用ARFIMA模型对金融市场条件收益率建模,运用GARCH、GJR、FIGARCH、APARCH、FIAPARCH等5种模型对金融波动率进行建模,进而运用极值理论(EVT)对标准收益的极端尾部风险建模来测度各股市的动态风险,并用返回测试(Back-testing)方法检验模型的适应性。实证结果表明,总的来说,FIAPARCH-EVT模型对各个市场具有较强的适应性,风险测度能力较为优越。进一步,本文在ARFIMA-FIAPARCH模型下,假定标准收益分别服从正态分布(N)、学生t分布(st)、有偏学生t分布(skst)、广义误差分布(GED)共4种分布,对各股市的动态风险测度的准确性进行检验,并和EVT方法的测度结果进行对比分析。结果表明,EVT方法风险测度能力优于其他方法,有偏学生t分布假设下的风险测度模型虽然略逊于EVT方法,但也不失为一种较好的方法;ARFIMA-FI-APARCH-EVT不仅在中国大陆沪深股市表现最为可靠,而且在其他市场也表现出同样的可靠性。