摘要
以江铜CWB1(580026)权证为样本,将标的股票价格和权证规定的行权价格之比、无风险利率、波动率和权证到期期限作为输入,权证价格作为输出,利用支持向量回归和粒子群算法进行仿真分析和预测,发现经过PSO算法优化过的SVR方法对权证价格的仿真结果精度高,能够较好地拟合和预测样本权证价格。
This paper describes the principle and mathematical expression of support vector regression and particle swarm optimization algorithm. Taken as input were the proportion of the underlying stock price to the executive price of warrant, risk-free interest rate, maturity volatility and maturity warrants, with warrant price as output. Based on the simulation results, the PSO-SVR has achieved high precision and offered a good fitting and precision of the warrants price.
出处
《广州大学学报(社会科学版)》
2010年第4期56-59,81,共5页
Journal of Guangzhou University:Social Science Edition
基金
广东省哲学社会科学"十一五"规划2008年度学科共建项目(08GE-10)