基于影响力传动的Kuramoto股市预测模型  

Stock market Kuramoto forecasting model based on influence transmission

作　　者：戚国全 王浩[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2016年第6期761-766,共6页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61070131;61175051;61175033)

摘　　要：文章基于同步振子Kuramoto模型,提出了影响力传动的Kuramoto股市趋势预测模型(IT-KFM)。IT-KFM模型运用贝叶斯网络构建振子之间的结构关系,引入影响力传动,给出传动因子量化方法,将传动因子的传动参数加入到原Kuramoto模型中,进而根据不同振子间相位协方差的趋势变化分析和预测股市趋势,实验结果证明,IT-KFM算法相对于标准的SVM网络,在股票的走势预测方面有较好的预测效果。Based on the synchronous vibrator Kuramoto model ,a stock market trends forecasting model with influence transmission （IT-KFM ） is presented .In IT-KFM algorithm ,Bayesian network is uti-lized to build the structural relationships between the oscillators ,and the influence transmission is in-troduced .Then the quantitative method of transmission factor is given ,and the transmission parame-ters of transmission factor are added to the original Kuramoto model .Finally ,the stock market trends are analyzed and forecasted according to the trend change of the covariance between different oscillator phases .The experimental results show that the performance of the proposed method is better than the standard SVM algorithm in stock trend forecast .

关 键 词：KURAMOTO 模型 贝叶斯网络 股市预测 影响力 传动因子 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构] F830.91[自动化与计算机技术—计算机科学与技术]