基于压力测试的我国某商业银行房贷违约率评估  

Mortgage default rate appraisal of Chinese commercial bank applied with stress testing method

作　　者：孙玉莹[1] 闫妍[2,3] 

机构地区：[1]中国科学院数学与系统科学研究院,北京100190 [2]中国科学院大学管理学院,北京100080 [3]国家信息中心,北京100045

出　　处：《系统工程理论与实践》2014年第9期2235-2244,共10页Systems Engineering-Theory & Practice

基　　金：国家自然科学基金(71103179;71102129);广义虚拟经济研究专项(GX2011-1019(Y));中国政法大学青年教师学术创新团队资助项目

摘　　要：运用带外生变量的自回归模型和向量误差修正模型对房价下跌背景下商业银行的不良贷款率问题进行了研究.以房地产不良贷款率度量信用风险,以居民消费价格指数、贷款利率、商品房平均销售价格、汇率、仿泰德利差和广义货币供应量作为压力指标变量,建立了合适的房贷压力测试模型.在贷款利率上升、商品房销售价格下跌的压力情境下,分别预测了房地产不良贷款率的变化路径.实证结果表明,在压力情景下,不良贷款率先急剧上升,然后逐渐降低并趋于稳定,在影响因素中,房价对房地产不良贷款率的影响程度最强,持续时间最长.Applied with autoregressive exogenous model and vector error correction model,this article analyzes the nonperforming-loan rate of a commercial bank based on the house price falling scenario.Nonperforming-loan ratio is used to describe the credit risk and the pressure indicators,including CPI,lending rates,house prices,exchange rates,TED spread and M2,are used to construct the stress testing model of house loan.This article forecasts the fluctuations of nonperforming-loan ratios between the second quarter of 2010 and the first quarter of 2011 under the assumption of the lending rate rising and house prices falling.The results suggest that the nonperforming-loan ratios will rise sharply first,and then slow down to be steady in the stress scenarios.Among all of those factors,house price is the most influential one and its influence lasts the longest.

关 键 词：压力测试 不良贷款率 带外生变量的自回归模型 向量误差修正模型 仿泰德利差 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]