位置：成果数据库 > 期刊 > 期刊详情页
基于支持向量机的集团信用风险预警研究
  • 期刊名称：中国农业大学学报　2008 ,13 (2),p94298
  • 时间：0
  • 分类：F830.9[经济管理—金融学]
  • 作者机构：[1]中国农业大学理学院,北京100083
  • 相关基金：国家自然科学基金资助项目（10631070;60573158;10771213）
  • 相关项目：图像处理中最优化方法的研究
关键词： 支持向量机, 巴塞尔新资本协议, 企业集团, 信用风险预警, 逻辑回归, support vector machine, Basel II, enterprise group, credit risk early-warning, logistic regression
中文摘要：

针对我国现有信用风险预警模型普遍以单一企业为样本，无法反映集团信用风险状况的问题，采用支持向量机算法，建立了企业集团信用风险预警指标体系，利用全国大额贷款和授信企业集团客户样本数据进行训练，提出了基于支持向量机的集团信用风险预警模型。理论分析及预警数值试验结果表明：基于支持向量机的集团信用风险预警模型与传统的基于逻辑回归算法预警模型相比，具有更好的泛化能力；在相同预警敏感水平下，采用前者预警的假负率为16．67％，与后者的23．45％相比具有更高的预警精度。基于支持向量机的集团信用风险预警模型可较好的应用于企业集团信用风险预警领域中。

英文摘要：

In order to forecast the group credit risk that currently couldn＇t be reflected in the credit risk early-warning system based on the sample of a single enterprise, an index system for a group credit risk early-warning was set up based on support vector machine （SVM） and trained using the national loan and confer group dataset. Finally a group credit risk early-warning system based on SVM was established. The results of theoretical analysis and numerical experiment indicated that the early-warning system based on SVM could reduce the false negative rate from 23.45% to 16.67% compared with the early-warning system based on logistic regression under the same level of sensitivity, which means this model has an obvious advantage of generalization and a higher early-warning precision.

同期刊论文项目
不确定信息处理中的最优化方法
期刊论文 24 会议论文 4
生物信息学与最优化方法
期刊论文 71 会议论文 25
图像处理中最优化方法的研究
期刊论文 28 会议论文 9
同项目期刊论文
消费者多方购买行为与企业R&D策略博弈分析
存在多方购买下网络外部性产品差异化策略博弈分析
基于层次分析法的石油开发项目投资风险评估
基于支持向量机与反K近邻的分类算法研究
项目投资中的风险评价指标及其量化方法
股市噪声交易有效性研究——新农公司股票收益分析
基于通径分析的应急管理风险监控和预防法
On the stability of the solution for multiobjective generalized games with the payoffs perturbed
基于层次聚类的大样本加权支持向量机
快速支持向量机增量学习算法
K-RSVCR: A rough margin-based multi-class support vector machine
一种改进的基于RS与SVM的故障诊断方法
基于结合空间信息的FCM聚类的分水岭图像分割
具有动态级联结构的在线Boosting算法
基于边缘检测函数尺度变换的水平集图像分割
改进的整体变分模型在视频图像修补上的应用
遗传算法的粗糙集理论在文本降维上的应用
小波变换和变分PDE相结合的图像去噪算法
产品多方面差异下双寡头定位定价模型
在消费者偏好不确定下双寡头定位定价博弈
基于改进变分水平集的红外图像分割算法
一种结合灰度边缘信息的高分辨率遥感影像纹理分割方法
一种改进的基于粗糙集与支持向量机的故障诊断方法
基于结合空间信息的FCM聚类的分水岭图像分割
具有动态级联结构的在线Boosting算法
用粗糙集理论评价生物质固体成型燃料技术
An optimizing reduced PLSMFE formulation for non-stationary conduction–convection problems
不同消费者分布下双寡头产品差异化策略博弈分析
A Novel Time Series Prediction Algorithm Basedon Support Vector Regression and Its Application To
核主成分分析（KPCA）在企业经济效益评价中的应用
一种求解分类问题的新算法
基于主成分分析与支持向量机的商业银行信贷风险评估
基于投影寻踪和支持向量机的模式识别方法
基于结合空间信息的FCM 聚类的分水岭图像分割
一种新的关联规则抽样算法
具有共振的高阶多点边值问题解的存在性
基于粗糙集理论的上市公司评价模型
基于主成分分析和支持向量机的商业银行信贷风险评估
一种处理多类分类问题的强化支持向量机方法
具有变号非线性项的二阶三点微分方程组的边值问题的2组正解
基于层次聚类的大样本加权支持向量机
A linear programming model based on network flow for pathway inference
Self-organizing map of complex networks for community detection
Protein evolution in yeast transcription factor subnetworks
An information-flow-based model with dissipation, saturation and direction for active pathway infere
SANA: an algorithm for sequential and non-sequential protein structure alignment
Detecting disease associated modules and prioritizing active genes based on high throughput data
Coordinating pricing and inventory control in a fluctuating environment
Binary matrix factorization for analyzing gene expression data
Prediction of protein-RNA binding sites by a random forest method with combined features
Sequence-based protein-protein interaction prediction via support vector machine
双聚类的关联规则挖掘方法
Biomolecular network querying: a promising approach in systems biology
Bridging protein local structures and protein functions
The knowledge-integrated network biomarkers discovery for Major Adverse Cardiac Events
Clustering complex networks and biological networks by nonnegative matrix factorization with various
二阶m点边值问题的多个正解存在性
Uncertainty of consumer preferences and product differentiation in two three-stage Hotelling models
基于在线学习的目标跟踪方法研究
一种多输出支持向量机的增量学习算法
基于在线学习的目标跟踪方法研究
Remarks on Network Community Properties
稳健的支持向量分类机的优化理论分析
Quantitative function for community detection
Recognition of structure similarities in proteins
Self-organizing map approaches for the haplotype assembly problem
Detecting drug targets with minimum side effects in metabolic networks
Cross-platform method for identifying candidate network biomarkers for prostate cancer
Exploring the constrained maximum edge-weight connected graph problem
Identifying differentially expressed pathways via a mixed integer linear programming model
一种求解分类问题的新算法
线性支持向量顺序回归机的原始问题的解集分析
Discovering functions and revealing mechanisms at molecular level from biological networks
A trust region method for optimization problem with singular solutions
Predicting gene ontology functions from protein's regional surface structures
Uncovering fuzzy community structure in complex networks
Hubs with Network Motifs Organize Modularity Dynamically in the Protein-Protein Interaction Network
Identification of overlapping community structure in complex networks using fuzzy c-means clustering
Graph kernels, hierarchical clustering, and network community structure: Experiments and comparative
Alignment of molecular networks by integer quadratic programming
Convergence analysis of adaptive trust region methods
不含4，5，6-圈的平面图的均匀染色
森林的非正常均匀染色
一些平面图的无圈边染色
基于非单调线搜索非拟牛顿法的全局收敛性
基于可能性理论的模糊支持向量分类机
NEW ROBUST UNSUPERVISED SUPPORT VECTOR MACHINES