本文選題：原油價格預(yù)測 + 壓縮感知�。� 參考：《北京化工大學(xué)》2015年碩士論文

【摘要】：國際原油價格自從1970年開始頻繁波動。它不僅受到基本的供求影響,同時也受到許多其他因素的綜合影響,包括天氣、存貨水平、經(jīng)濟增長、政治因素、心理期待甚至是一些非常規(guī)突發(fā)事件。多因素的影響導(dǎo)致原油價格序列呈現(xiàn)出非線性、非平穩(wěn)性、季節(jié)性、不規(guī)則性能一系列復(fù)雜特征。在這種情況下,本文引入了一種新的基于壓縮感知的人工智能預(yù)測方法來預(yù)測原油價格。具體來說,該方法引入了壓縮感知的兩種技術(shù),分別為壓縮感知去噪方法和稀疏分解方法并將其作為原油價格序列的預(yù)處理方法,然后基于這兩種數(shù)據(jù)處理方法分別構(gòu)造了兩種模型。一種是基于壓縮感知去噪的人工智能預(yù)測模型,另一種是基于稀疏分解的分解集成預(yù)測模型。基于壓縮感知去噪的人工智能預(yù)測模型是基于去噪預(yù)測的思想,首先采用壓縮感知去噪方法來對原始油價序列進行去噪的預(yù)處理,以減少噪聲數(shù)據(jù)對人工智能預(yù)測方法建模效果的影響,然后使用智能預(yù)測算法對去噪后的數(shù)據(jù)進行建模和預(yù)測。基于稀疏分解的分解集成預(yù)測模型是基于分解集成預(yù)測的思想,首先根據(jù)原油價格序列所表現(xiàn)出來的多種特性,構(gòu)造了一個過完備字典,并基于該字典將原油價格序列分解為不同的特征分量,然后使用前饋神經(jīng)網(wǎng)絡(luò)對分量進行建模和預(yù)測,最后將各個預(yù)測結(jié)果集成為最終的預(yù)測結(jié)果。本文對基于壓縮感知的兩種模型分別使用了WTI的日度原油價格和月度原油價格來進行實證分析,并得出以下結(jié)論：一方面,基于壓縮感知的兩種預(yù)測模型與基準(zhǔn)模型比較時均獲得最高的預(yù)測精度,表明基于壓縮感知的預(yù)測方法的有效性；另一方面,在不同數(shù)據(jù)集預(yù)測中,該框架下的兩種預(yù)測模型也都獲得了最高的預(yù)測精度,驗證了該方法的穩(wěn)定性。此外,實證結(jié)果也表明該方法在預(yù)測具有復(fù)雜非線性特征時間序列方面特別有效。
[Abstract]:International crude oil prices have fluctuated frequently since 1970. It is affected not only by basic supply and demand, but also by many other factors, including weather, inventory level, economic growth, political factors, psychological expectation and even some unconventional emergencies. Because of the influence of many factors, crude oil price series presents a series of complex characteristics, such as nonlinear, non-stationary, seasonal and irregular. In this case, a new artificial intelligence prediction method based on compression perception is introduced to predict crude oil price. Specifically, this method introduces two kinds of compression sensing techniques, namely, compressed perception denoising method and sparse decomposition method, which are used as pretreatment methods of crude oil price sequence. Then two models are constructed based on these two data processing methods. One is an artificial intelligence prediction model based on compressed perceptual denoising, the other is a decomposed integrated prediction model based on sparse decomposition. The artificial intelligence prediction model based on compressed perceptual de-noising is based on the idea of denoising and forecasting. Firstly, the compressed perceptual de-noising method is used to pre-process the original oil price sequence. In order to reduce the influence of noise data on the modeling effect of artificial intelligence prediction method, the model and prediction of de-noised data are modeled and predicted by using intelligent prediction algorithm. The decomposition integrated prediction model based on sparse decomposition is based on the idea of decomposing integrated prediction. Firstly, an overcomplete dictionary is constructed according to the characteristics of crude oil price series. Based on the dictionary, the crude oil price series is decomposed into different characteristic components, and then the feedforward neural network is used to model and predict the components. Finally, the prediction results are integrated into the final prediction results. In this paper, we use WTI's daily crude oil price and monthly crude oil price to analyze the two models based on compression perception, and draw the following conclusions: on the one hand, The two prediction models based on compressed perception obtain the highest prediction accuracy when compared with the reference model, which indicates the validity of the prediction method based on compressed perception. On the other hand, in different data sets, The two prediction models under this framework also obtain the highest prediction accuracy and verify the stability of the method. In addition, the empirical results show that this method is especially effective in predicting time series with complex nonlinear characteristics.
【學(xué)位授予單位】：北京化工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：F416.22;F764.1

【共引文獻】

相關(guān)期刊論文 前6條

1 王輝;譚國蘋;王雙成;;經(jīng)濟增長影響因素分析的動態(tài)貝葉斯網(wǎng)絡(luò)方法[J];東北師大學(xué)報(自然科學(xué)版);2013年04期

2 陳榮達;虞歡歡;;基于啟發(fā)式算法的支持向量機選股模型[J];系統(tǒng)工程;2014年02期

3 陳建志;文慧;楊淡漪;陳璐;凌語蓉;;金融時間序列分析中小波方法應(yīng)用研究[J];金融經(jīng)濟;2013年16期

4 范曉;;我國價格預(yù)測方法文獻研究[J];開發(fā)研究;2014年05期

5 谷政;盧亞娟;;通貨膨脹與農(nóng)業(yè)股票收益多尺度分析[J];技術(shù)經(jīng)濟與管理研究;2014年10期

6 陳艷;王子健;趙澤;李棟;崔莉;;傳感器網(wǎng)絡(luò)環(huán)境監(jiān)測時間序列數(shù)據(jù)的高斯過程建模與多步預(yù)測[J];通信學(xué)報;2015年10期

相關(guān)博士學(xué)位論文 前3條

1 王楠;基于NDF與NARX網(wǎng)絡(luò)的人民幣匯率預(yù)測研究[D];大連理工大學(xué);2013年

2 白云;時間序列特性驅(qū)動的供水量預(yù)測方法研究及應(yīng)用[D];重慶大學(xué);2014年

3 熊濤;基于EMD的時間序列預(yù)測混合建模技術(shù)及其應(yīng)用研究[D];華中科技大學(xué);2014年

相關(guān)碩士學(xué)位論文 前3條

1 陳仁磊;瓦斯時間序列混沌特性分析及預(yù)測研究[D];燕山大學(xué);2014年

2 廉潔;改進的內(nèi)容分析排序算法在搜索引擎中的研究與應(yīng)用[D];大連交通大學(xué);2013年

3 鐘燕敏;公路網(wǎng)縣域微循環(huán)系統(tǒng)規(guī)劃布局研究[D];武漢輕工大學(xué);2014年

，

本文編號：1828449