Density Function Estimation Based on SVM: An Application in Estimating Liquidity Risk in Stock Market
This paper presents a method to compute liquidity risk of stock market with model of VaR. Firstly, a measure for liquidity is defined, which reflects the volatility of return caused by unit ratio of the position to be liquidated to the tradable shares. Secondly, the density function of the measure for liquidity is estimated with support vector machine, with which the liquidity VaR of stocks is calculated. Finally, some stocks of Shanghai and Shenzhen stock markets are chosen, according to their tradable shares, to compute liquidity VaR. The results show that the liquidity VaR is bigger than the traditional VaR that is calculated without considering liquidity, which means the latter does underestimate the risk.
Yiwen Yang Chenxi Zhang
School of Management of Northwestern Polytechnical University, Xi’an, Shannxi 710072 China
国际会议
2009 IEEE International Conference on Grey System and Intelligent Services(2009 IEEE灰色系统与服务科学国际会议)
南京
英文
1570-1574
2009-10-20（万方平台首次上网日期，不代表论文的发表时间）