基于符号序列方法的股价指数预测研究

用两种符号序列方法分别对上证指数进行实证统计分析。一种是以日收盘价计算的指数价差的符号序列,另一种是以每日5分钟高频数据计算的多重分形谱参数符号序列。统计结果表明,指数的涨落不是完全随机的,两种方法都能以一定的条件概率来预测指数的涨落;进一步地,在引入股价指数大涨落的阈值和条件平均增益后,发现大幅涨落时,条件与指数变化的关联性比小的涨落要强得多,而且将两种符号序列方法结合可以更好地预测指数的大涨落。

The Forecasting Research of Stock Price Index by the Symbol Sequence

Using two kinds of symbol sequence as the condition, this paper presents an empirical research on the data of Shanghai Stock Price Index. One is the symbol sequence of difference of daily closing quotation indexes; the other is the symbol sequence of multifractal spectrum parameter of the high frequency data ticked every 5 minitues. The re- sult shows that, the fluctuating of index is not random totally, and both of these two conditional probabilities have the forecasting capacity. In addition, it is found that the relation between the condition of different symbol sequences and changes of index in larger fluctuating of stock price index is stronger than the relation in smaller fluctuating of stock price index when threshold values are introduced. And the combining of these two methods has remarkable forecasting capacity.