基于加权支持向量机的VaR计算方法研究  

A New Var Model Based on Weighted Support Vector Machine

作　　者：胡莹[1] 王安民[1] 

机构地区：[1]西安电子科技大学经济管理学院,陕西西安710071

出　　处：《经济数学》2010年第1期53-60,共8页Journal of Quantitative Economics

摘　　要：针对统计学框架下传统VaR计算方法的不足,发展了基于加权支持向量机(W-SVM)的VaR计算新方法.为了在VaR模型中计入金融时间序列的记忆效应,采用最优市场因子作为支持向量机的加权模型.对2001-2009年上证综指的实证研究表明,基于W-SVM的VaR模型优于传统的VaR方法,在小样本、厚尾、非线性及有异常波动的市场条件下,各种置信度下的W-SVM方法均能取得较好的性能.According to the defects of the traditional VaR computation methods in the statistics frame- work, a new VaR model based on weighted support vector machine （W-SVM） was investigated. In order to deal with the memory effect in the financial time serials, a weighted model based on optimal market factor was introduced. The Shanghai composite index from the year 2001 to 2009 was modeled, and the simulation results indicated that the new VAR method based W-SVM was better than traditional methods. Even for small sample ,abnormal fluctuations and heavy tails in nonlinear market, W SVM model can obtain good performance at different confidence intervals.

关 键 词：在险风险值 支持向量机 概率密度估计 上证综指 

分 类 号：F830.9[经济管理—金融学]