基于证据理论与多源信息融合的银行信贷客户评价  

Bank Credit Client Assessment Based on DS Theory and Data Fusion Algorithm

作　　者：钟文[1] 刘纯平[2] 朱近[1] 夏德深[1] 

机构地区：[1]南京理工大学计算机科学与技术系,南京210094 [2]苏州大学计算机科学与技术学院,苏州215006

出　　处：《南京理工大学学报》2003年第6期691-695,714,共6页Journal of Nanjing University of Science and Technology

摘　　要：银行信贷过程中将不可避免地涉及到信贷客户的各种不确定信息,采用证据理论方法,在建立识别框架和基本概率分配函数基础上,从特征级和决策级2个层面,通过计算和统计分析,得到客户的信任度和似然度2个结论,用这2个结论构成的信任区间,指导银行信贷的经办、决策人员的工作,促进工作的有效开展。In the process of bank credit, the uncertain information will inevitably appeard, some information of credit clients. Using the DS evidence theory based on the frame of discernment and the basic probability assignment function, the conclusions of belief function and plausibility function from feature layer and decision layer are obtained. By applying the belief section of two conclusions, it is active and effective for tasks of transactors and decision makers of bank credit.

关 键 词：证据理论 信息融合 决策支持 客户评价 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程] F830.5[自动化与计算机技术—控制科学与工程]