基于粗糙集理论的决策树方法在贷款客户信用评估中的应用

决策树是数据挖掘中常用的分类技术，其生成的规则便于决策者理解和应用。然而面对较多的属性且含有冗余和噪声属性的记录集生成的决策树时，无法删除冗余属性，造成运算过程复杂。本文旨在通过应用粗糙集理论，将其与决策树方法进行结合，对属性进行约简，降低运算复杂度，并生成相对简化的规则形式，并将其应用到银行个人贷款客户信用评估之中。     

Cost monotonicity, consistency and minimum cost spanning tree games

We propose a new cost allocation rule for minimum cost spanning tree games. The new rule is a core selection and also satisfies cost monotonicity. We also give characterisation theorems for the new rule as well as the much-studied Bird allocation. We show that the principal difference between these two rules is in terms of their consistency properties.     

Generalizations of Ho–Lee’s binomial interest rate model I: from one- to multi-factor

In this paper a multi-factor generalization of Ho–Lee model is proposed. In sharp contrast to the classical Ho–Lee, this generalization allows for those movements other than parallel shifts, while it still is described by a recombining tree, and is a process with stationary independent increments to be compatible with principal component analysis. Based on the model, generalizations of duration-based hedging are proposed. A continuous-time limit of the model is also discussed. This research was supported by Open Research Center Project for Private Universities: matching fund subsidy from MEXT, 2004–2008 and also by Grants-in-Aids for Scientific Research (No. 18540146) from the Japan Society for Promotion of Sciences.     

基于实物期权法对R&D项目价值评估的研究——对布莱克-舒尔斯定价模型的改进

针对R&D项目投资的特点,探讨了采用布莱克一舒尔斯期权定价模型对R&D项目价值评估可能存在的缺陷,并提出一种改进方法,即将决策树和布莱克一舒尔斯定价模型结合运用,因为决策树能够模拟研发项目的阶段性决策过程,考虑到多个离散型不确定性因素的相关性,模拟并计算出对决策路径依赖的现金流,因此能克服纯粹使用布莱克一舒尔斯公式的不足,在考虑多个不确定性因素的影响下,实现对多阶段R&D项目价值的评估,作出正确的投资决策。     

基于灰关联法发动机故障诊断的研究

应用灰关联理论对发动机的故障进行诊断。灰关联分析属非函数型的序列模式,能有效处理杂散数据。通过建立工程机械发动机系统故障树,运用灰关联分析对关联度进行计算及排序,给出各种故障模式发生的可能性排序,从而为处理故障、控制故障的发生以及改进系统的可靠性提供理论依据。     

宁波市天一广场盆栽大树移植技术探讨

本文以天一广场盆栽大树成功移植经验为基础,详细论述了城市绿化建设中特殊条件下大树移植发方法,以期对类似园林工程施工有所帮助。     

我国股改中权证的价格泡沫及影响因素

本文针对我国股改中的百慕大权证提出了新的“模拟树-市场情绪”定价模型。该模型的实证研究结果表明中国权证市场价格存在严重高估;加入市场情绪指标后,通过建立多元回归模型得到了对于实际价格的显著的拟合结果,有力地解释了超出权证理论价格的实际价格所包含的情绪因素。本文最后对权证价格高估的原因及权证未来的走势进行了分析。     

论以粮换林换草与河西地区的可持续发展--以武威地区为例

分析了武威地区可持续发展的主要生态环境问题,讨论了生态恢复与重建面临的困境,论证了以粮换林换草对促进区域可持续发展的必要性和有效性,指出了以粮换林换草中应进一步研究的问题,提出生态重建要坚持多措施并举。     

An effective going concern prediction model for the sustainability of enterprises and capital market development

The purpose of this study is to construct a two-stage effective and innovative going concern prediction model to predict going concern doubt for the sustainability of enterprises and capital market development. Samples of this study are the companies listed on the Taiwan Stock Exchange or the Taipei Exchange, totalling 196 companies and including 49 companies with going concern doubt and 147 normal companies (with no going concern doubt). The data are taken from the Taiwan Economic Journal (TEJ) and the Market Observation Post System during the period from 2001 to 2016 (totalling 16 years). This study adopts a two-stage way to construct the going concern prediction models. In Stage I, the traditional statistical method of stepwise regression (SR) and the data mining technique artificial neural network (ANN) are applied to select the important variables. In Stage II, two decision tree algorithms (data mining techniques): classification and regression tree (CART) and C5.0 are used to establish the prediction models. The results show that the SR + CART model has the highest going concern prediction accuracy, with an overall accuracy of 87.42%.     

Machine learning in individual claims reserving

Machine learning techniques make it feasible to calculate claims reserves on individual claims data. This paper illustrates how these techniques can be used by providing an explicit example in individual claims reserving.