根據(jù)股票市場(chǎng)是非線性動(dòng)力系統(tǒng)的假設(shè)，利用混沌理論對(duì)混沌時(shí)間序列的分析方法，提出了股票價(jià)格預(yù)測(cè)方法。同時(shí)利用重構(gòu)相空間的嵌入維數(shù)和延遲時(shí)間分別確定經(jīng)向基函數(shù)模型網(wǎng)絡(luò)的結(jié)構(gòu)和訓(xùn)練樣本對(duì)，對(duì)實(shí)際的股票時(shí)間序列預(yù)測(cè)結(jié)果表明，該方法能有效地進(jìn)行短期預(yù)測(cè)，并與前饋神經(jīng)網(wǎng)絡(luò)模型相比，可得到較好的預(yù)測(cè)結(jié)果，因而在股票時(shí)間序列預(yù)測(cè)中有廣泛的實(shí)用價(jià)值。
關(guān) 鍵 詞 混沌時(shí)間序列; 股票價(jià)格; 神經(jīng)網(wǎng)絡(luò); 預(yù)測(cè)

Abstract A method of stock price prediction is presented by hypothesis of stock market being non-linear dynamic system and analyzing method of chaos theory for chaos time series in this paper. Meanwhile, structures of radial basic function (RBF) network and pairs of training samples are determined by embedding dimension and delay time of reconstruct phase space respectively. Predicting results for real world stock time series show that the method is able to do effectively short-term prediction. In comparison with traditional forward feedback neural network (BP), the method can make better predicting performance, thus it can be widely used in stock price prediction.
Key words chaotic time series; stock price; neural network; prediction