基于人工免疫机制的个人信用风险模型研究  

Study of Consumer Credit Model Based on Artificial Immunity Mechanism

作　　者：杨雨[1] 

机构地区：[1]中央财经大学管理工程学院,北京100081

出　　处：《管理评论》2006年第9期17-20,共4页Management Review

基　　金：北京市科学技术委员会北京软科学博士学位论文基金资助(ZZ0519)

摘　　要：个人信用风险模型已经被普通应用于银行的业务中。随着同业竞争的加剧和信息的增加,伴随计算科学的进步和网络技术的发展,模型向着智能化方向发展。本文在人工免疫原理的框架下,将免疫机制应用于个人信用风险模型中,提出了双边抗体人工免疫概率模型。指出了人工免疫原理中各个机制的实现方法。并对该模型方法和逻辑回归模型方法的预测能力进行了比较。Consumer credit model has been applied in the business of banks. Increasing competition, expanding information and growing computation science and network technology are leading models to be more intelligent. In this paper immunity algorithm is applied in the consumer credit model under the theoretical framework of artificial immunity and Bilateral Antibody Artificial Immune Probability Model is presented. The paper also demonstrates the theoretical framework of consumer credit model based on artificial immunity system, and describes ways of realizing each mechanism of the immunity theory. It compares Bilateral Antibody Artificial Immune Probability Model and Logistic Regression Model in terms of their capacity of forecasting.

关 键 词：双边抗体 人工免疫 概率模型 信用风险模型 个人信用 

分 类 号：F224[经济管理—国民经济]