基于D-S证据理论的存货质押融资贷前风险评价

存货质押融资贷前风险评价是银行规避风险、选择优质客户的重要手段。建立了存货质押融资贷前风险评价指标体系,提出了多源异类信息指标的mass函数表达与处理方法,基于D-S证据理论建立了风险评价模型。为克服传统定性指标的专家权重赋值方法主观性较强的缺陷,基于Jousselme证据间距离提出了一种综合权重赋值方法。实例分析表明,该模型可直观地度量存货质押融资业务的风险水平,帮助银行准确、快速地审核贷款企业的存货质押融资贷款申请。     

Der Wertbeitrag von Prozessflexibilität

Promising to cope with increasing demand variety and uncertainty, flexibility in general and process flexibility in particular are becoming ever more desired corporate capabilities. During the last years, the business process management and the production/operations management communities have proposed numerous approaches that investigate how to valuate and determine an appropriate level of process flexibility. Most of these approaches are very restrictive regarding their application domain, neglect characteristics of the involved processes and outputs other than demand and capacity, and do not conduct a thorough economic analysis of process flexibility. Against this backdrop, the authors propose an optimization model that determines an appropriate level of process flexibility in line with the principles of value-based business process management. The model includes demand uncertainty, variability, criticality, and similarity as process characteristics. The paper also reports on the insights gained from applying the optimization model to the coverage switching processes of an insurance broker pool company.     

Forecasting credit portfolio components with a Markov chain model

We consider the forecasting problem for components of a bank’s credit portfolio, in particular, for the share of non-performing loans. We assume that changes in the portfolio are described by a Markov random process with discrete time and finite number of states. By the state of a loan we mean that it belongs to a certain group of loans with respect to the existence and duration of arrears. We assume that the matrix of transitional probabilities is not known exactly, and information about it is collected during the system’s operation.     

Towards the construction of workflow-suitable conceptual modelling techniques

Despite their high-level and graphical nature, workflow specifications require a significant amount of implementation detail — for example application programming interface, database access and programming mechanisms for information flow — for a more comprehensive validation than is currently possible. This is currently recognized as a deficiency in workflow conceptualization. Although conceptual modelling techniques are available which are expressive, comprehensive and precise enough, we believe, their concepts and features are not specialized enough for workflow domains. In this paper, we offer a comparative insight into techniques which characterize different aspects and approaches of workflow specifications. These are: structured process modelling, object-oriented modelling, behavioural process modelling and business-oriented modelling. In particular, we determine gaps for workflows capturing operational business transaction processing, for example those of insurance claims, bank loans and government-related registration. For technique construction, we describe five workflow suitability principles.     

Visa moves towards COPAC Mark II

Banks want to build their customer base and they see the ‘unbanked’ population as a large, unexploited market for loans and services. But banks want customers who will make their loan interest payments on time. Many of the unbanked are unbanked because they cannot show a record of servicing loans. Is there a way out of this dilemma?     

Modelling the credit risk for portfolios of consumer loans: Analogies with corporate loan models

The New Basel accord has highlighted the need for models of the credit risk in portfolios of consumer loans. There are really no such models of the risks in consumer loan portfolios even though there is a well established industry – credit scoring – in modelling the risk of individual loans. Yet there are a number of models of the credit risk of portfolios of corporate loans. This paper discusses if and how one could use equivalent approaches to building such models in consumer lending even if the models themselves cannot translate across because of the assumptions underlying them.     

When is a good time to refinance?

Because of inertia and wish effect, businesses hurt their own future by refusing to take advantage of low interest rates. As a business builds up its equity in the capital structure, the firm could refinance to take advantage of leverage financing. Even when the capital structure is unchanged, the firm may wish to refinance because of a low interest rate. But the business may not refinance because of inertia and wish effect. Decision makers have been reluctant to refinance due to high interest rates. Even when the new rate is lower, they wait for an even better rate. They keep the old high rate and do nothing about it, wishing for the good old days of low interest rates. They just do not venture into new opportunities because of the lack of capital. The nation's economy and productivity are hurt.

This paper examines refinancing situations of firms and individuals who use long term loans. The paper then develops four decision models for typical refinancing situations considering such factors as old and new interest rates, capital structure in terms of debt/equity ratio, loan amount, transaction cost, expected rate of return from the best opportunity available, expected inflation rate, and possible changes in interest rates in the future.

Based on the decision models, a computerized Refinancing Decision System (RDS) has been developed. The paper discusses the functions and uses of the system showing how each of the decision models has been incorporated in the system.

The RDS is a good tool in evaluating refinancing decision situations for individual owners of income properties and similar real properties subject to long term mortgage loans and for the managers of firms that hold plants and have expansion plans. The System can be very useful for the general home owners too, if they wish to reduce the monthly payments of their mortgage loan interest.     

Assessing loan risks: a data mining case study

The USDA's (US Department of Agriculture) Rural Housing Service administers a loan program that lends or guarantees mortgage loans to people living in rural areas. To administer these nearly 600000 loans, the department maintains extensive information about each one in its data warehouse. As with most lending programs, some USDA loans perform better than others. Basic data mining techniques helped the USDA's Rural Housing Service better understand and classify problem loans     

借用国外贷款决策系统的设计与实现

将商务智能解决方案(数据仓库,在线联机分析,数据挖掘)应用于决策系统成为现在较为普遍的做法。以借用国外贷款决策系统为例,介绍了建立借用国外贷款决策系统的意义和作用,详细阐述了系统的设计与实现过程。将开发的系统应用于《山西省借用国外贷款25年回顾与总结》项目,并取得了成功。     

基于CVaR和Monte Carlo仿真的贷款组合决策模型

提供了一种新的贷款组合决策优化方法，该模型用更能反映贷款组合信用风险特征的CVaR作为风险度量。由于在实际中很难获取各笔贷款的历史数据，为此给出了一种基于Matlab语言的Monte Carlo仿真方法。从而使谊模型可以通过线性规划技术有效的进行求解。最后给出了一个例子。     

Expert system-user integrated adaptive systems

Many expert systems operate in dynamic environments where various pertinent environmental variables and conditions vary with the passage of time. These environmental variables and conditions may affect both the set of conditions applied to input variables of expert systems and the set of recommendations provided by expert systems. For this reason, expert systems developed according to dynamic structure will generate timely recommendations. To incorporate dynamic characteristics into the structure of expert systems, it is necessary to develop expert systems as adaptive systems. This paper intends to integrate concepts of learning and adaptiveness into expert system technology.

Expert systems used to assist loan officers in improving the decision-making process of commercial loans are typical examples of expert systems that operate in dynamic environments. This paper illustrates that the quality of information provided to loan officers by expert systems may be improved when expert systems are designed as adaptive expert systems.     

使用ARIS进行动态业务流程建模

为了能够在当今高度竞争的商业环境中生存和发展,企业需要不断改进自身的业务流程。显然,对业务流程进行动态建模可以大大提高项目重新设计的成功可能。本文对利用ARIS进行业务流程进行动态建模做了可行性研究;同时,文章还对业务流程模型的仿真进行了讨论。最后本文给出了一个关于ARIS动态建模应用在保险公司的实例。     

Mining demand chain knowledge of life insurance market for new product development

Demand chain management (DCM) can be defined as “extending the view of operations from a single business unit or a company to the whole chain. Essentially, demand chain management focuses not only on generating drawing power from customers to purchase merchandises on the supply chain; but also on exploring satisfaction, participation, and involvement from customers in order for enterprises to understand customer needs and wants. Thus, customers have changed their position in the demand chain to assume a leading role in bringing more benefit for enterprises. This article investigates what functionalities best fit the consumers’ needs and wants for life insurance products by extracting specific knowledge patterns and rules from consumers and their demand chain. By doing so, this paper uses the a priori algorithm and clustering analysis as methodologies for data mining. Knowledge extraction from data mining results is illustrated as market segments and demand chain analysis on life insurance market in Taiwan in order to propose suggestions and solutions to the insurance firms for new product development and marketing.     

The evaluation of consumer loans using support vector machines

The commencement of the Basel II requirement, popularization of consumer loans and the intense competition in financial market has increased the awareness of the critical delinquency issue for financial institutions in granting loans to potential applicants. In the past few decades, the scheme of artificial neural networks has been successfully applied to the financial field. Recently, the Support Vector Machine (SVM) has emerged as the better neural network in dealing with classification and forecasting problems due to its superior features of generalization performance and global optimum. This study develops a loan evaluation model using SVM to identify potential applicants for consumer loans. In addition to conducting experiments on performance comparison via cross-validation and paired t test, we analyze misclassification errors in terms of Type I and Type II and their effect on selecting network parameters of SVM. The analysis findings facilitate the development of a useful visual decision-support tool. The experimental results using a real-world data set reveal that SVM surpasses traditional neural network models in generalization performance and visualization via the visual tool, which helps decision makers determine appropriate loan evaluation strategies.     

基于规则引擎的金融风控系统

金融科技企业推出了以小额现金贷为主导产品的一种新型金融模式：P2P网络借贷模式。现金贷产品自推出以来，在很短的时间内就积累了大量的客户。如何制定快速有效的金融风控策略，提高客户信息数据处理效率，及时预测防范业务中信用及欺诈风险，成为金融企业亟待解决的问题。对此，本文提出基于规则引擎的金融风控模型，实现风控规则策略和程序硬编码的解耦，在此基础上进行特征因子以及特征模型的设计，对于实现金融科技企业信贷体系中的自动化审批将起到很大的推动作用。     

基于信用担保的资金约束供应链订货与定价决策

受自由现金流的限制, 中小企业需要外部融资来实现良性运营, 供应商信用担保贷款是一种有效手段. 考虑银行下侧风险控制的担保贷款模型, 根据供应链购销过程中的订货量和批发价参数决策, 评价供应链内部无风险资本转移过程. 通过建立供应商担保费率、风险担保比率设计和银行利率组合模型, 确定贷款担保系统的最优决策. 研究结果表明: 在具有贷款可获得性的资金约束供应链中, 存在最优订货量与批发价的组合, 且供应商销售收入存在最值; 在担保贷款过程中, 存在最优风险分担比例, 通过设计合理的风险控制模型, 可提高零售商资金水平, 达到供应链的协同.

     

容灾系统研究

随着IT系统的广泛深入应用,IT系统的高可用性和容灾能力问题日益成为一个关注的焦点,容灾系统的建设对于国防、政府、企业都有着重要的意义.容灾系统的目标在于提高IT系统的生存能力,保障业务流程的连续性,减少因各种灾难而造成的损失.该文依照工程化的思想,以容灾系统生命周期模型为基础,提出了容灾系统的需求分析和设计方法,并对主要的容灾技术进行了比较分析.     

决策树算法在农户小额贷款中的应用研究

在讨论数据挖掘技术的基本概念、决策树方法的基础上,针对近年来农村信用社不良贷款的增加,提出了决策树算法在农户小额信用贷款评价中的应用。利用数据挖掘的预测功能,建立了一种较为科学明了,简单易行的农户信用评价模型,来应用于农村信用社对农户信用的评分,以作为贷款与否的依据。     

Survival and success of family‐owned small businesses after hurricane Katrina: Impact of disaster assistance and adaptive capacity

The study's purpose is to examine the relative importance of direct disaster assistance to family‐owned small firms on their survival and success while considering the components of their adaptive capacity after experiencing Hurricane Katrina. This study employed data from the 2013 and 2015 Small Business Survival and Demise after a Natural Disaster Project (SBSD), a project funded by the National Science Foundation. The logistic regression results show that family businesses with SBA loans (or loan guarantees) were significantly more likely to survive. In addition, family businesses where household and family issues were more frequently in conflict with work demands were more likely to survive. On the other hand, the OLS regression results indicate that family businesses with more stress and more family–business conflict were less likely to succeed.     

International comparison of bubbles and bubble indicators

The purpose of this paper is to analyze the financial turmoil of the US subprime loan crisis of mid-Noughties and to compare it with the Japanese asset bubble of late 1980s. While examining the two crises, it compares the monetary policies of both countries, focusing on the excess liquidity and expansion of bank loans that were seen. This paper develops several bubble indicators, including the ratio of real estate loans to total loans, the loan-to-GDP ratio, and housing affordability. In order to develop these indicators, it is necessary to compare banking behavior in both Japan and the United States, as banks in both countries were making loans beyond the point of profit maximization. Property prices and monetary policy in both countries influenced banking behavior significantly. The bubble indicators developed in this paper can be used as early warning indicators for future bubbles.