本校學位論文庫
CITYU Theses & Dissertations
論文詳情
陈仪
鄺婉樺
金融學院
金融學博士學位課程(中文學制)
博士
2023
基於CEEMDAN-PCA-BPMs模型的金融時間序列預測
Prediction of Financial Time Series Based on CEEMDAN-PCA-BPMs Model
金融時間序列預測 ; CEEMDAN-PCA-BPMs預測
financial time series forecasting ; CEEMDAN-PCA-BPMs forecasting
公開日期：22/6/2027
本文以滬深300指數的日線數據為研究對象並輔之以上證50ETF指數收盤價和倫敦金收盤價時間序列作為實證驗證，所選的時間序列區間為2/1/2018-8/5/2024，以此作為探究如何使用智慧算法科技對數據進行挖掘，構建一個科學合理的智慧預測模型，這樣可以為投資者規避風險、現投資增值保值，另一方面，本文採用的先把數據進行分解後組合預測，這樣使得原本存在非線性、非平穩特徵的數據變得平穩、簡化其特征，這樣有利於後續的預測研究。
本文具體內容如下：①對金融時間序列進行分解並結合相應金融理論進行分析；②對金融時間序列的預測研究當中結合時代背景貼合數據的特徵提出一個新的預測模型。③為了驗證CEEMDAN-PCA-BPMs模型的預測效果，該模型會對上證50ETF指數收盤價和倫敦金收盤價時間序列進行預測實證分析。④為了驗證CEEMDAN-PCA-BPMs模型的預測效果，該模型會與ARIMA、RNN模型和組合模型進行對比分析。
實證結果表明,CEEMDAN-PCA-BPMs模型的預測效果是最優的,这个分别可以见于模型对于三种金融时间序列进行预测可得，其中对于CEEMDAN-PCA-BPMs对滬深300的預測指标MAE、MAPE、MSE和R2分別為20.780508、0.005659、642.374451和 0.995566,在預測效能上明顯優於其他模型，再者，該模型對上證50ETF指數的預測效果為MAE、MAPE、MSE和R2分别为0.014686、0.005808、0.000336和0.991678。對倫敦金收盤價時間序列的預測效果分別為MAE、MAPE、MSE和R2分別為14.360964 、0.007099、380.378235和0.990461。
對於數據的分析是有必要,這樣科研工作者從對數據的分析當中得出結果從而迴響結果到現實的生活生產當中,再者,對於投資者而言,尤其是股票投資者,提醒投資者在投資過程中要保持一定的理性,非理性的投資心理容易在短時間內對市場造成一定的衝擊。
本文具體內容如下：①對金融時間序列進行分解並結合相應金融理論進行分析；②對金融時間序列的預測研究當中結合時代背景貼合數據的特徵提出一個新的預測模型。③為了驗證CEEMDAN-PCA-BPMs模型的預測效果，該模型會對上證50ETF指數收盤價和倫敦金收盤價時間序列進行預測實證分析。④為了驗證CEEMDAN-PCA-BPMs模型的預測效果，該模型會與ARIMA、RNN模型和組合模型進行對比分析。
實證結果表明,CEEMDAN-PCA-BPMs模型的預測效果是最優的,这个分别可以见于模型对于三种金融时间序列进行预测可得，其中对于CEEMDAN-PCA-BPMs对滬深300的預測指标MAE、MAPE、MSE和R2分別為20.780508、0.005659、642.374451和 0.995566,在預測效能上明顯優於其他模型，再者，該模型對上證50ETF指數的預測效果為MAE、MAPE、MSE和R2分别为0.014686、0.005808、0.000336和0.991678。對倫敦金收盤價時間序列的預測效果分別為MAE、MAPE、MSE和R2分別為14.360964 、0.007099、380.378235和0.990461。
對於數據的分析是有必要,這樣科研工作者從對數據的分析當中得出結果從而迴響結果到現實的生活生產當中,再者,對於投資者而言,尤其是股票投資者,提醒投資者在投資過程中要保持一定的理性,非理性的投資心理容易在短時間內對市場造成一定的衝擊。
This article takes the daily data of the Shanghai and Shenzhen 300 Index as the research object, supplemented by the time series of the closing price of the SSE 50ETF Index and the London Gold closing price as empirical verification. The selected time series interval is 2/1/2018-8/5/2024, which is used to explore how to use intelligent algorithm technology to mine data and construct a scientific and reasonable intelligent prediction model. This can help investors avoid risks and maintain investment value. On the other hand, this article adopts the method of first decomposing the data and then combining them for prediction, making the data that originally had nonlinear and non-stationary characteristics stable and simplifying its features, which is conducive to subsequent prediction research.
The specific content of this article is as follows: ①Decompose financial time series and analyze it in conjunction with corresponding financial theories; ②A new prediction model is proposed in the study of financial time series prediction, which combines the characteristics of the era background and data To verify the predictive performance of the CEEMDAN-PCA-BPMs model, the model will conduct empirical analysis on the time series of the closing price of the Shanghai Stock Exchange 50ETF index and the London gold closing price To verify the predictive performance of the CEEMDAN-PCA-BPMs model, it will be compared and analyzed with ARIMA、RNN model and combination models.
The empirical results show that the CEEMDAN-PCA-BPMs model has the best predictive performance, which can be seen from the model's predictions of three financial time series. Among them, the MAE, MAPE, MSE, and R2 of CEEMDAN-PCA-BPMs for the Shanghai and Shenzhen 300 are 20.780508，0.005659，642.374451，and 0.995566, respectively, which are significantly better than other models in terms of predictive performance. Furthermore, the model's predictive performance of MAE, MAPE, MSE, and R2 for the Shanghai 50ETF index is 0.014686，0.005808，0.000336，and 0.991678，respectively. The predictive effects on the London gold closing price time series are MAE, MAPE, MSE, and R2, which are 14.360964 ,0.007099,380.378235, and 0.990461, respectively.
It is necessary to analyze data so that researchers can draw results from the analysis of data and reflect them in real life and production. Furthermore, for investors, especially stock investors, it is important to maintain a certain level of rationality in the investment process. Unreasonable investment psychology can easily cause a certain impact on the market in a short period of time.
The specific content of this article is as follows: ①Decompose financial time series and analyze it in conjunction with corresponding financial theories; ②A new prediction model is proposed in the study of financial time series prediction, which combines the characteristics of the era background and data To verify the predictive performance of the CEEMDAN-PCA-BPMs model, the model will conduct empirical analysis on the time series of the closing price of the Shanghai Stock Exchange 50ETF index and the London gold closing price To verify the predictive performance of the CEEMDAN-PCA-BPMs model, it will be compared and analyzed with ARIMA、RNN model and combination models.
The empirical results show that the CEEMDAN-PCA-BPMs model has the best predictive performance, which can be seen from the model's predictions of three financial time series. Among them, the MAE, MAPE, MSE, and R2 of CEEMDAN-PCA-BPMs for the Shanghai and Shenzhen 300 are 20.780508，0.005659，642.374451，and 0.995566, respectively, which are significantly better than other models in terms of predictive performance. Furthermore, the model's predictive performance of MAE, MAPE, MSE, and R2 for the Shanghai 50ETF index is 0.014686，0.005808，0.000336，and 0.991678，respectively. The predictive effects on the London gold closing price time series are MAE, MAPE, MSE, and R2, which are 14.360964 ,0.007099,380.378235, and 0.990461, respectively.
It is necessary to analyze data so that researchers can draw results from the analysis of data and reflect them in real life and production. Furthermore, for investors, especially stock investors, it is important to maintain a certain level of rationality in the investment process. Unreasonable investment psychology can easily cause a certain impact on the market in a short period of time.
2024
中文
119
致 謝 III
摘 要 IV
Abstract VI
圖目錄 X
表目錄 XI
第一章 緒 論 12
1.1 研究背景 12
1.2 研究問題 16
1.3 研究意義 17
1.3.1 研究理論意義 17
1.3.2 研究實踐意義 18
1.5 研究目標及內容 19
1.5.1 研究目標 19
1.5.2 研究內容 20
1.6 本文成果以及創新點 20
第二章 基礎理論與文獻綜述 22
2.1 分形市場假說（Fractal Market Hypothesis,FMH） 22
2.2 投資者情緒理論 23
2.3 雜訊交易與股票市場價格時間序列理論研究 24
2.4 金融時間序列模型研究文獻 25
2.5 迴圈神經網路（Recurrent Neural Network, RNN）相關文獻綜述 31
2.6 CEEMDAN-PCA-BPMs模型相關文獻綜述 32
2.6.1 反向傳播算法（Backpropagation Neural Network） BP研究狀況 32
2.6.2 支持向量機（Support Vector Machine）SVM研究狀況 37
2.6.3 極限學習機（Extrem Learning Machine）ELM研究狀況 40
2.6.4 核極限學習機（Kernel Extrem Learning Machine）KELM模型研究現狀 43
2.6.5 長短期記憶神經網路（Long Short Term Memory）LSTM研究现状 48
2.6.6 自我調整雜訊的完全集成經驗模態分解（CEEMDAN）的研究現狀 52
2.6.7 主成分分析（PCA）研究現狀 59
2.6.8 學術研究分析 60
2.7 本章小結 62
第三章 金融時間序列預測模型研究方法 64
3.1 文獻閱讀法 64
3.2 對比分析法 64
3.3 經驗總結法 64
3.4 時間序列預測模型 65
3.5 對照模型 65
3.6 單一算法原理 65
3.6.1 差分自回归移动平均模型(Autoregressive Integrated Moving Average Model,简记ARIMA) 65
3.6.2 迴圈神經網路（Recurrent Neural Network, RNN） 66
3.6.3 反向傳播算法（Backpropagation Neural Network） BP神經網路 66
3.6.4 支持向量機（Support Vector Machine）SVM 67
3.6.5 極限學習機（Kernel Extreme Learning Machine- Extreme Learning Machine）原理 68
3.6.6 長短期記憶（Long Short Term Memory）LSTM 68
3.6.7 具有自我調整雜訊的完整集成經驗模態分解（CEEMDAN） 69
3.6.8 主成分分析法（Principal Component Analysis）PCA的概念 70
3.6.9 BPMs模型構建 70
3.7 評估標準 71
3.8 CEEMDAN-PCA-BPMs模型構建流程圖 72
3.9 本章小結 72
第四章 實證結果分析討論 74
4.1 預測指數的CEEMDAN-PCA-BPMs模型及實證結果 74
4.2 CEEMDAN對分解結果 76
4.3 关于CEEMDAN-PCA-BPMs模型中期运行结果展示 79
4.4 模型預測誤差比較 93
4.5本章小結 101
第五章 結論與建議 105
5.1 結論 105
5.2 建議 107
5.3 研究限制 111
5.4 後續研究 111
作者簡歷 119
摘 要 IV
Abstract VI
圖目錄 X
表目錄 XI
第一章 緒 論 12
1.1 研究背景 12
1.2 研究問題 16
1.3 研究意義 17
1.3.1 研究理論意義 17
1.3.2 研究實踐意義 18
1.5 研究目標及內容 19
1.5.1 研究目標 19
1.5.2 研究內容 20
1.6 本文成果以及創新點 20
第二章 基礎理論與文獻綜述 22
2.1 分形市場假說（Fractal Market Hypothesis,FMH） 22
2.2 投資者情緒理論 23
2.3 雜訊交易與股票市場價格時間序列理論研究 24
2.4 金融時間序列模型研究文獻 25
2.5 迴圈神經網路（Recurrent Neural Network, RNN）相關文獻綜述 31
2.6 CEEMDAN-PCA-BPMs模型相關文獻綜述 32
2.6.1 反向傳播算法（Backpropagation Neural Network） BP研究狀況 32
2.6.2 支持向量機（Support Vector Machine）SVM研究狀況 37
2.6.3 極限學習機（Extrem Learning Machine）ELM研究狀況 40
2.6.4 核極限學習機（Kernel Extrem Learning Machine）KELM模型研究現狀 43
2.6.5 長短期記憶神經網路（Long Short Term Memory）LSTM研究现状 48
2.6.6 自我調整雜訊的完全集成經驗模態分解（CEEMDAN）的研究現狀 52
2.6.7 主成分分析（PCA）研究現狀 59
2.6.8 學術研究分析 60
2.7 本章小結 62
第三章 金融時間序列預測模型研究方法 64
3.1 文獻閱讀法 64
3.2 對比分析法 64
3.3 經驗總結法 64
3.4 時間序列預測模型 65
3.5 對照模型 65
3.6 單一算法原理 65
3.6.1 差分自回归移动平均模型(Autoregressive Integrated Moving Average Model,简记ARIMA) 65
3.6.2 迴圈神經網路（Recurrent Neural Network, RNN） 66
3.6.3 反向傳播算法（Backpropagation Neural Network） BP神經網路 66
3.6.4 支持向量機（Support Vector Machine）SVM 67
3.6.5 極限學習機（Kernel Extreme Learning Machine- Extreme Learning Machine）原理 68
3.6.6 長短期記憶（Long Short Term Memory）LSTM 68
3.6.7 具有自我調整雜訊的完整集成經驗模態分解（CEEMDAN） 69
3.6.8 主成分分析法（Principal Component Analysis）PCA的概念 70
3.6.9 BPMs模型構建 70
3.7 評估標準 71
3.8 CEEMDAN-PCA-BPMs模型構建流程圖 72
3.9 本章小結 72
第四章 實證結果分析討論 74
4.1 預測指數的CEEMDAN-PCA-BPMs模型及實證結果 74
4.2 CEEMDAN對分解結果 76
4.3 关于CEEMDAN-PCA-BPMs模型中期运行结果展示 79
4.4 模型預測誤差比較 93
4.5本章小結 101
第五章 結論與建議 105
5.1 結論 105
5.2 建議 107
5.3 研究限制 111
5.4 後續研究 111
作者簡歷 119
1.丁文昌.（2022）.基於CEEMDAN-XGBoost的上證50ETF已實現波動率的研究（碩士學位論文，上海師範大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202202&filename=1022484364.nh
2. 文姣&張娜.（2023）.基於LSTM變權組合模型的股價預測.商展經濟（07）,95-97.doi:10.19995/j.cnki.CN10-1617/F7.2023.07.095.
3.毛遠宏,孫琛琛,徐魯豫,劉曦,柴波&賀鵬超.（2023）.基於深度學習的時間序列預測方法綜述.微電子學與電腦（04）,8-17.doi:10.19304/J.ISSN1000-7180.2022.0725.
4.牛振鑫.（2022）.面向數據分類的優化極限學習機理論研究（碩士學位論文,曲阜師範大學）.https://43.138.60.40/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1022058218.nh
5.王先.（2022）.基於EMD-XGBoost模型的BDI指數預測研究（碩士學位論文,大連海事大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1023465853.nh
6.王青天,孔越（2020）.金融科技介紹.InPython金融大數據風控建模實戰基於機器學習（pp.2–22）.essay,機械工業出版社.
7.王基厚，林培光，周佳倩，李慶濤，張燕&蹇木偉. （2021）.結合公司財務報表數據的股票指數預測方法.電腦應用（12），3632-3636.
8. 田聰.（2021）.基於改進型EMD-LSTM的高頻金融時間序列預測（碩士學位論文,江西財經大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202102&filename=1021614225.nh
9.任偉傑.（2020）.多元時間序列的特徵分析與建模研究（博士學位論文,大連理工大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cdfdlast2022&filename=1020145811.nh
10. 朱菊香,任明煜,穀衛&張雯柏.（2023）.基於CEEMDAN-IGWO-CNN-LSTM空氣品質預測建模.電腦模擬.
11. 次必聰&張品一.（2022）.基於ARIMA-LSTM模型的金融時間序列預測.統計與決策（11）,145-149.doi:10.13546/j.cnki.tjyjc.2022.11.029.
12. 吳川惠&王昭.（2021）.基於PSO算法優化BP神經網路的金融風險防範預警模型研究.大眾投資指南（11）,19-20.doi:CNKI:SUN:DATZ.0.2021-11-009.
13. 呂亞妮.（2022）.基於時間序列線性數學模型的電力系統短期負荷預測.光源與照明（07）,168-170.
14. 李悅.（2023）.基於深度神經網路的時間序列預測模型研究（碩士學位論文,遼寧師範大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1023583534.nh
15. 李海林&張麗萍.（2022）.時間序列資料挖掘中的聚類研究綜述.電子科技大學學報（03）,416-424.
16. 李博薇,邸夢醉,魏子鯤,李麗華,喬宏&趙浩然.（2023）.基於PCA-SSA-ELM模型的河北省雞蛋價格預測及預警.黑龍江畜牧獸醫（08）,1-7.doi:10.13881/j.cnki.hljxmsy.2022.07.0118.
17. 李璟璟.（2023）.基於CEEMDAN-PCA-LSTM的上證指數預測（碩士學位論文,蘭州大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1023598273.nh
18. 於孝建,劉國鵬,劉建林&肖煒麟..基於LSTM網絡和文字情感分析的股票指數預測.中國管理科學.doi:10.16381/j.cnki.issn1003-207x.2021.0084.
19. 林寒冰，金秀玲，王婷&林雲霞. （2022）.基於PCA-CNN的動態短文字分析研究.科技創新與應用（11），44-48+52.doi:10.19981/j.CN23-1581/G3.2022.11.007.
20. 侯木舟,駱家輝&羅秋懿.（2020）.基於變分模態分解的極限學習機在金融時間序列預測中的應用.數學理論與應用（04）,105-117.
21. 思曼,閆亮,張豔輝&蔡霞.（2023）.基於ARIMA-Intervention-LSTM的組合預測模型.河北工業大學學報（02）,28-34.doi:10.14081/j.cnki.hgdxb.2023.02.004.
22. 苗旭東,&魏連鑫.（2018）.基於小波和PSO-BP神經網路的金融時序預測.資訊技術,5.
23. 郎巨林&鄭晟.（2023）.基於CNN-RNN集成的隧道事故异常聲音識別.電子量測科技（20），164-169.doi:10.19651/j.cnki.emt.2212417.
24. 韋權&湯占軍.（2022）.基於SSA-VMD-SE-KELM結合蒙特卡洛法的風電功率區間預測.智慧電力（09）,59-66.
25. 唐旻&黃志剛.（2022）.引入投資者關注度的股指收益率預測研究——基於差分進化演算法極限學習機模型.系統科學與數學（06）,1503-1518.
26. 唐黎.（2018）.金融時間序列預測的資訊融合與計算智慧模型（博士學位論文,電子科技大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cdfdlast2018&filename=1018974841.nh
27. 孫中葉&徐曉燕.（2021）.農業供應鏈金融風險評估研究——基於GA-BP神經網路模型.科技經濟與管理研究（08）,78-82.doi:CNKI:SUN:JXJG.0.2021-08-015.
28. 徐玉春&郭靜.（2023）.基於BP神經網路算法和時間序列模型的氣溫預測方法.鄭州鐵路職業技術學院學報（03）,24-27.doi:10.13920/j.cnki.zztlzyjsxyxb.2023.03.002.
29. 徐寅祥.（2015）.我國股市雜訊交易對收益率的影響分析碩士學位論文,福建師範大學）. https://kns.cnki.net/kcms2/article/abstract?v=JTjHPEokuYS_Yb5oXw0gUzbCvuJe4c_kf -AooUWiBtDjpXVyvjqRbuCZ461guTxgX5XAK8LHD4WYqn24wg5NaZFbEvYD2UkRx87HD-XqEC-XKrgbVjT4ILdiPY_ 2OT5lbA2Q5a-BaqUM_ 3wUlLGlNg==uniplatform=NZKPTlanguage=CHS
30. 殷林飛&劉金元..基於人工情感LSTM算法的智慧家庭能量管理.綜合智慧能源.
31. 高斌.（2021）.基於各類EMD-深度神經網路的高頻金融數據預測研究（碩士學位論文,長春工業大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202102&filename=1021609173.nh
32. 崔金鑫&鄒輝文.（2020）.基於CEEMDAN-MR-PE-NLE多頻優化組合模型的碳金融市場價格預測.數學的實踐與認識（03）,105-120.
33. 張栗粽,王謹平,劉貴松,羅光春&盧國明.（2018）.面向金融數據的神經網路時間序列預測模型.電腦應用研究（09）,2632-2637.
34. 張攀.（2021）.基於BP神經網路的金融不良債權回收率評估研究.中國資產評估（04）,36-40.doi:CNKI:SUN:ZCPG.0.2021-04-008.
35. 梁宏濤,劉碩,杜軍威,胡强,&於旭（2023）.深度學習應用於時序預測研究綜述.計算機科學與探索,1.
36. 梁循（2012）。支持向量機算法及其金融應用。北京：國家智慧財產權局知識產權出版社。
37. 淩銘,肖麗英,趙嘉,王萍根,王寅,項凱&蔡高堂.（2023）.基於SVM-CEEMDAN-BiLSTM模型的日降水量預測.人民珠江（09）,61-68.
38. 郭璿.（2022）.基於BP神經網路的科技企業信貸風險評估實證研究.陝西理工大學學報（社會科學版）（05）,65-71.doi:CNKI:SUN:HZSF.0.2022-05-010.
39. 陳偉,石仕華,陳華勇,袁偉倩,羅睿寧&楊莉.（2021）.基於BP神經網路的特殊客戶群體金融服務優化研究——以小微企業信用評級研究為例.區域金融研究（12）,51-56.doi:CNKI:SUN:GXJR.0.2021-12-007.
40. 陳强.(2021).機器學習及Python應用：高等教育出版社.
41. 雪,鮑剛&龔順琦.（2022）.基於參數優化的KELM和GRU的短期電力負荷預測.電子器件（04）,931-938.
42. 彭蘋.（2023）.基於R語言ARIMA模型和LSTM模型的中藥材價格指數預測.長江資訊通信（08）,26-28.
43. 程文輝&車文剛.（2022）.基於二次分解與LSTM的金融時間序列預測算法研究.重慶郵電大學學報（自然科學版）（04）,638-645.
44. 楊亞男.（2022）.關於股票市場預測建模研究（碩士學位論文,浙江科技學院）.https://kns.cnki.net/kcms2/article/abstract?v=innwydrwifl0oo4udqjyaki8ipojdnb-0YGGoj0ex_ESVhZZrD0TKDT2seOvpc8aQaxrTyCUx2cgC7gRK_QlRXIz16CyRfW9tWMGJEoXpaf30M0qQtjDV9HyRl5qqdVK&uniplatform=NZKPT&language=CHS
45. 遊皓麟.R語言預測實戰[M].北京：電子工業出版社,2017年第一版.
46. 熊思亦&熊永良.（2023）.基於CEEMDAN-LSTM組合方法的海平面變化預測分析.大地測量與地球動力學（09）,899-903.doi:10.14075/j.jgg.2023.09.004.
47. 管學英.（2024）.基於ARIMA-RNN混合模型的股價預測.哈爾濱商業大學學報（自然科學版）（02），250-256.doi:10.19492/j.cnki.1672-0946.2024.02.008.
48. 趙博宇.（2021）.機器學習在匯率預測中的組合研究（碩士學位論文,浙江大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202102&filename=1021626577.nh
49. 趙煜&韓旭昊.（2023）.基於CEEMDAN-LSTM組合的蘭州空氣品質指數預測.安徽師範大學學報（自然科學版）（05）,433-439+447.doi:10.14182/J.cnki.1001-2443.2023.05.004.
50. 趙煜&韓旭昊.（2023）.基於CEEMDAN-LSTM組合的蘭州空氣品質指數預測.安徽師範大學學報（自然科學版）（05），433-439+447.doi:10.14182/J.cnki.1001-2443.2023.05.004.
51. 劉揚&杜帥兵.（2023）.基於改進EMD-SSA-KELM的用水量預測方法研究.人民黃河（06）,73-78+85.
52. 劉磊.（2023）.投資者網絡情緒指數構建及其在股市指數預測建模中的應用研究（碩士學位論文,西北大學）.https://kns.cnki.net/kcms2/article/abstract?v=kiaz1sjia-71qqMIscF5uWePOomNM2W83VouNO_yHkTW0KGD3SPVCUcpedcTIiL61-Z67nwks5bMimDUyc1TGWI51XNwYTY72oiKm9iFp9oUrDRhe2tRLprUj_YKhR7KIptaZhSgJmM=&uniplatform=NZKPT&language=CHS
53. 劉穎,李惠迪&譚博元.（2022）.基於多源數據深度融合的金融時間序列預測.統計與決策（23）,52-56.doi:10.13546/j.cnki.tjyjc.2022.23.010.
54. 潘和平&張承釗.（2018）.FEPA-金融時間序列自我調整組合預測模型.中國管理科學（06）,26-38.doi:10.16381/j.cnki.issn1003-207x.2018.06.004.
55. 蔔鈺家.（2022）.基於GA-BP神經網路的成都市房價預測模型.現代電腦（20）,98-102.doi:CNKI:SUN:XDJS.0.2022-20-019.
56. 學峰張亞濤. （2021）.資本市場開放能够降低雜訊交易程度嗎？—— 基於滬港通的經驗證據.金融科學（02）,23-39.
57. 錢子傑.（2021）.基於ICEEMDAN-GWO-MKELM的金融時間序列預測（碩士學位論文,西南財經大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202202&filename=1021735972.nh
58. 錢吳永&張浩男.（2022）.基於Adaboost-DPSO-SVM模型的供應鏈金融信用風險評估研究.工業技術經濟（03）,72-79.doi:CNKI:SUN:GHZJ.0.2022-03-007.
59. 龍馬高新教育.（2018）.Python3資料分析與機器學習實戰-預測分析.InPython3資料分析與機器學習實戰（pp.165–168）.essay,北京大學出版社.
60. 薛薇.（2021）.Python機器學習原理與實踐-數據預測中的相關問題.InPython機器學習原理與實踐（pp.54–56）.essay,中國人民大學出版社.
61. 謝遊宇&王萬雄（2023）..基於EMD和SSA的股票預測模型.電腦工程與應用.
62. 韓志遠.（2023）.基於數據差分的LSTM模型庫存商品需求預測.中國儲運（09）,152-153.doi:10.16301/j.cnki.cn12-1204/f.2023.09.114.
63. 韓璐,蘇治&劉志東.（2020）.金融市場的協動預測模型：DWT-SVM方法.系統科學與數學（12）,2342-2356.
64. 叢敬奇,成鵬飛&趙振軍..基於CEEMD-CNN-LSTM的股票指數集成預測模型.系統工程.
65. 聶良剛&蘭瑞樂.（2023）.基於ICOA優化極限學習機的網安態勢預測.電腦工程與設計（04）,998-1006.doi:10.16208/j.issn1000-7024.2023.04.006.
66. 聶軼文&王韡. （2023）.基於PCA-GA-BP神經網路模型對安徽省物流需求量預測.阜陽師範大學學報（自然科學版）（04），96-102.doi:10.14096/j.cnki.cn34-1069/n/2096-9341（2023）04-0096-07.
67. 羅子幸. （2021）.雜訊交易對我國證券市場的影響研究.科技資訊（19）,190-192.doi:10.16661/j.cnki.1672-3791.2106-5042-2879.
68. 羅志丹.（2023）.數據驅動的金融時間序列混合預測模型研究與實證分析（博士學位論文,對外經濟貿易大學）.https://kns.cnki.net/kcms2/article/abstract?v=kiaz1sjia-5AUA7XvgQ8v9ZYnWjNYF_kZOps-VZ6l1A0yHBO83udWFdO8PeR-Jf2jhs2B8JsaWmfPJyvxd0MO3xPbANLcB2jbkH7Tu9XeliubNhv87tMSMUpsgY0ab1HsnpbrliH5II=&uniplatform=NZKPT&language=CHS
69. 蘇礦喜.（2022）.基於EMD去噪算法的股市投資組合研究（博士學位論文,華中師範大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cdfdlast2023&filename=1022084394.nh
70. Bao,Y.,Lu,Y.,&Zhang,J.(2004).Forecasting stock price by SVMs regression.In Artificial Intelligence: Methodology, Systems, and Applications: 11th International Conference, AIMSA 2004, Varna, Bulgaria, September 2-4, 2004. Proceedings 11 (pp.295-303).Springer Berlin Heidelberg.
71. Belavadi, S. V., Rajagopal, S., Ranjani, R., & Mohan, R. (2020). Air quality forecasting using LSTM RNN and wireless sensor networks. Procedia Computer Science, 170, 241-248.
72. Black, F. (1986). Noise. The journal of finance, 41(3), 528-543.
73. Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of econometrics, 31(3), 307-327.
74. Bouktif, S., Fiaz, A., Ouni, A., & Serhani, M. A. (2020). Multi-sequence LSTM-RNN deep learning and metaheuristics for electric load forecasting. Energies, 13(2), 391.
75. Box,G.E.,Jenkins,G.M.,Reinsel,G.C.,&Ljung,G.M.(2015).Time series analysis: forecasting and control. JohnWiley&Sons.
76. Cameron, A. C., & Windmeijer, F. A. (1997). An R-squared measure of goodness of fit for some common nonlinear regression models. Journal of econometrics, 77(2), 329-342.
77. Cao, J., Li, Z., & Li, J. (2019). Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical mechanics and its applications, 519, 127-139.
78. Cao, L., & Tay, F. E. (2001). Financial forecasting using support vector machines. Neural Computing & Applications, 10, 184-192.
79. ChaiT, D. R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE). Arguments againstavoiding RMSEintheliterature, 7(1), 1247.
80. Chen, F., Chen, J., & Liu, J. (2022). Forecast of flood disaster emergency material demand based on IACO-BP algorithm. Neural Computing and Applications, 1-13.
81. Chen, Y., & Khong, E. (2022). A stacked forecasting model-CEEMDAN-BPMs model. Academic Journal of Computing & Information Science, 5(9), 82-89.
82. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297.
83. De Long, J. B., Shleifer, A., Summers, L. H., & Waldmann, R. J. (1990). Noise trader risk in financial markets. Journal of political Economy, 98(4), 703-738.
84. De Myttenaere, A., Golden, B., Le Grand, B., & Rossi, F. (2016). Mean absolute percentage error for regression models. Neurocomputing, 192, 38-48.
85. Dubois, D. J., Prade, H., & Yager, R. R. (Eds.). (2014). Readings in fuzzy sets for intelligent systems. Morgan Kaufmann.
86. Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica: Journal of the econometric society, 987-1007.
87. Engle, R. F., Lilien, D. M., & Robins, R. P. (1987). Estimating time varying risk premia in the term structure: The ARCH-M model. Econometrica: journal of the Econometric Society, 391-407.
88. Fan, J., & Yao, Q. (2003). Nonlinear time series: nonparametric and parametric methods (Vol. 20). New York: Springer.
89. Fang,T.,Zheng,C.,&Wang,D.(2023).Forecasting the crude oil prices with an EMD-ISBM-FNNmodel.Energy,263,125407.
90. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232.
91. Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network. In Neural networks for perception (pp. 65-93). Academic Press.
92. Hochreiter,S.,&Schmidhuber,J.(1997).Long short-term memory. Neural computation, 9(8),1735-1780.
93. Huang, G. B., Zhou, H., Ding, X., & Zhang, R. (2011). Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 42(2), 513-529.
94. Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1-3), 489-501.
95. Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., ... & Liu, H. H. (1998). The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 454(1971), 903-995.
96. Huang,Y.,Yu,J.,Dai,X.,Huang,Z.,&Li,Y.(2022).Air-quality prediction based on the EMD–IPSO–LSTM combination model.Sustainability,14(9),4889.
97. Jamei, M., Ali, M., Malik, A., Karbasi, M., Rai, P., & Yaseen, Z. M. (2023). Development of a TVF-EMD-based multi-decomposition technique integrated with Encoder-Decoder-Bidirectional-LSTM for monthly rainfall forecasting. Journal of Hydrology, 617, 129105.
98. Khemakhem, S., & Boujelbene, Y. (2018). Predicting credit risk on the basis of financial and non-financial variables and data mining. Review of accounting and finance, 17(3), 316-340.
99. Liu, D., Liu, C., Fu, Q., Li, T., Imran, K. M., Cui, S., & Abrar, F. M. (2017). ELM evaluation model of regional groundwater quality based on the crow search algorithm. Ecological Indicators, 81, 302-314.
100.Liu, N., Tang, Q., Zhang, J., Fan, W., & Liu, J. (2014). A hybrid forecasting model with parameter optimization for short-term load forecasting of micro-grids. Applied Energy, 129, 336-345.
101.Liu, Y., Zhao, Q., Yao, W., Ma, X., Yao, Y., & Liu, L. (2019). Short-term rainfall forecast model based on the improved BP–NN algorithm. Scientific reports, 9(1), 19751.
102.Meng,D.,Wang,H.,Yang,S.,Lv,Z.,Hu,Z.,&Wang,Z.(2022).Fault analysis of wind power rolling bearing based on EMD feature extraction.CMES-Computer Modeling in Engineering & Sciences,130(1),543-558.
103.Meyer, D., & Wien, F. T. (2001). Support vector machines. R News, 1(3), 23-26.
104.N-BEATS-RNN: Deep learning for time series forecasting. In 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 765-768). IEEE.
105.Nelson, D. B. (1992). Filtering and forecasting with misspecified ARCH models I: Getting the right variance with the wrong model. Journal of econometrics, 52(1-2), 61-90.
106.Pan,H.(2011).A basic theory o fintelligent finance.New Mathematics and Natura lComputation,7(02),197-227.
107.Parida, N., Mishra, D., Das, K., & Rout, N. K. (2021). Development and performance evaluation of hybrid KELM models for forecasting of agro-commodity price. Evolutionary Intelligence, 14, 529-544.
108.Qin, J., Tao, Z., Huang, S., & Gupta, G. (2021, March). Stock price forecast based on ARIMA model and BP neural network model. In 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) (pp. 426-430). IEEE.
109.Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied soft computing, 90, 106181.
110.Stein, J. C. (1996). Rational capital budgeting in an irrational world.
111.Tay, F. E., & Cao, L. (2001). Application of support vector machines in financial time series forecasting. omega, 29(4), 309-317.
112.Wang, R., Peng, C., Gao, J., Gao, Z., & Jiang, H. (2020). A dilated convolution network-based LSTM model for multi-step prediction of chaotic time series. Computational and Applied Mathematics, 39, 1-22.
113.Wang, Z., & Bovik, A. C. (2009). Mean squared error: Love it or leave it? A new look at signal fidelity measures. IEEE signal processing magazine, 26(1), 98-117.
114.Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, 30(1), 79-82.
115.Xu, Q., & Kong, W. (2021, July). Research on forecast model based on BP neural network algorithm. In Journal of Physics: Conference Series (Vol. 1982, No. 1, p. 012065). IOP Publishing.
116.Yang, R., Yu, L., Zhao, Y., Yu, H., Xu, G., Wu, Y., & Liu, Z. (2020). Big data analytics for financial Market volatility forecast based on support vector machine. International Journal of Information Management, 50, 452-462.
117.Yu, L., Chen, H., Wang, S., & Lai, K. K. (2008). Evolving least squares support vector machines for stock market trend mining. IEEE transactions on evolutionary computation, 13(1), 87-102.
118.Zhang, W., Qu, Z., Zhang, K., Mao, W., Ma, Y., & Fan, X. (2017). A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting. Energy conversion and management, 136, 439-451.
119.Zhang, Y. (2019). Application of improved BP neural network based on e-commerce supply chain network data in the forecast of aquatic product export volume. Cognitive Systems Research, 57, 228-235.
120.Zhang, Y., & Wang, Y. (2023). Forecasting crude oil futures market returns: A principal component analysis combination approach. International Journal of Forecasting, 39(2), 659-673.
121.Zhou, C., Yin, K., Cao, Y., Intrieri, E., Ahmed, B., & Catani, F. (2018). Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method. Landslides, 15, 2211-2225.
2. 文姣&張娜.（2023）.基於LSTM變權組合模型的股價預測.商展經濟（07）,95-97.doi:10.19995/j.cnki.CN10-1617/F7.2023.07.095.
3.毛遠宏,孫琛琛,徐魯豫,劉曦,柴波&賀鵬超.（2023）.基於深度學習的時間序列預測方法綜述.微電子學與電腦（04）,8-17.doi:10.19304/J.ISSN1000-7180.2022.0725.
4.牛振鑫.（2022）.面向數據分類的優化極限學習機理論研究（碩士學位論文,曲阜師範大學）.https://43.138.60.40/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1022058218.nh
5.王先.（2022）.基於EMD-XGBoost模型的BDI指數預測研究（碩士學位論文,大連海事大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1023465853.nh
6.王青天,孔越（2020）.金融科技介紹.InPython金融大數據風控建模實戰基於機器學習（pp.2–22）.essay,機械工業出版社.
7.王基厚，林培光，周佳倩，李慶濤，張燕&蹇木偉. （2021）.結合公司財務報表數據的股票指數預測方法.電腦應用（12），3632-3636.
8. 田聰.（2021）.基於改進型EMD-LSTM的高頻金融時間序列預測（碩士學位論文,江西財經大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202102&filename=1021614225.nh
9.任偉傑.（2020）.多元時間序列的特徵分析與建模研究（博士學位論文,大連理工大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cdfdlast2022&filename=1020145811.nh
10. 朱菊香,任明煜,穀衛&張雯柏.（2023）.基於CEEMDAN-IGWO-CNN-LSTM空氣品質預測建模.電腦模擬.
11. 次必聰&張品一.（2022）.基於ARIMA-LSTM模型的金融時間序列預測.統計與決策（11）,145-149.doi:10.13546/j.cnki.tjyjc.2022.11.029.
12. 吳川惠&王昭.（2021）.基於PSO算法優化BP神經網路的金融風險防範預警模型研究.大眾投資指南（11）,19-20.doi:CNKI:SUN:DATZ.0.2021-11-009.
13. 呂亞妮.（2022）.基於時間序列線性數學模型的電力系統短期負荷預測.光源與照明（07）,168-170.
14. 李悅.（2023）.基於深度神經網路的時間序列預測模型研究（碩士學位論文,遼寧師範大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1023583534.nh
15. 李海林&張麗萍.（2022）.時間序列資料挖掘中的聚類研究綜述.電子科技大學學報（03）,416-424.
16. 李博薇,邸夢醉,魏子鯤,李麗華,喬宏&趙浩然.（2023）.基於PCA-SSA-ELM模型的河北省雞蛋價格預測及預警.黑龍江畜牧獸醫（08）,1-7.doi:10.13881/j.cnki.hljxmsy.2022.07.0118.
17. 李璟璟.（2023）.基於CEEMDAN-PCA-LSTM的上證指數預測（碩士學位論文,蘭州大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfdtemp&filename=1023598273.nh
18. 於孝建,劉國鵬,劉建林&肖煒麟..基於LSTM網絡和文字情感分析的股票指數預測.中國管理科學.doi:10.16381/j.cnki.issn1003-207x.2021.0084.
19. 林寒冰，金秀玲，王婷&林雲霞. （2022）.基於PCA-CNN的動態短文字分析研究.科技創新與應用（11），44-48+52.doi:10.19981/j.CN23-1581/G3.2022.11.007.
20. 侯木舟,駱家輝&羅秋懿.（2020）.基於變分模態分解的極限學習機在金融時間序列預測中的應用.數學理論與應用（04）,105-117.
21. 思曼,閆亮,張豔輝&蔡霞.（2023）.基於ARIMA-Intervention-LSTM的組合預測模型.河北工業大學學報（02）,28-34.doi:10.14081/j.cnki.hgdxb.2023.02.004.
22. 苗旭東,&魏連鑫.（2018）.基於小波和PSO-BP神經網路的金融時序預測.資訊技術,5.
23. 郎巨林&鄭晟.（2023）.基於CNN-RNN集成的隧道事故异常聲音識別.電子量測科技（20），164-169.doi:10.19651/j.cnki.emt.2212417.
24. 韋權&湯占軍.（2022）.基於SSA-VMD-SE-KELM結合蒙特卡洛法的風電功率區間預測.智慧電力（09）,59-66.
25. 唐旻&黃志剛.（2022）.引入投資者關注度的股指收益率預測研究——基於差分進化演算法極限學習機模型.系統科學與數學（06）,1503-1518.
26. 唐黎.（2018）.金融時間序列預測的資訊融合與計算智慧模型（博士學位論文,電子科技大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cdfdlast2018&filename=1018974841.nh
27. 孫中葉&徐曉燕.（2021）.農業供應鏈金融風險評估研究——基於GA-BP神經網路模型.科技經濟與管理研究（08）,78-82.doi:CNKI:SUN:JXJG.0.2021-08-015.
28. 徐玉春&郭靜.（2023）.基於BP神經網路算法和時間序列模型的氣溫預測方法.鄭州鐵路職業技術學院學報（03）,24-27.doi:10.13920/j.cnki.zztlzyjsxyxb.2023.03.002.
29. 徐寅祥.（2015）.我國股市雜訊交易對收益率的影響分析碩士學位論文,福建師範大學）. https://kns.cnki.net/kcms2/article/abstract?v=JTjHPEokuYS_Yb5oXw0gUzbCvuJe4c_kf -AooUWiBtDjpXVyvjqRbuCZ461guTxgX5XAK8LHD4WYqn24wg5NaZFbEvYD2UkRx87HD-XqEC-XKrgbVjT4ILdiPY_ 2OT5lbA2Q5a-BaqUM_ 3wUlLGlNg==uniplatform=NZKPTlanguage=CHS
30. 殷林飛&劉金元..基於人工情感LSTM算法的智慧家庭能量管理.綜合智慧能源.
31. 高斌.（2021）.基於各類EMD-深度神經網路的高頻金融數據預測研究（碩士學位論文,長春工業大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202102&filename=1021609173.nh
32. 崔金鑫&鄒輝文.（2020）.基於CEEMDAN-MR-PE-NLE多頻優化組合模型的碳金融市場價格預測.數學的實踐與認識（03）,105-120.
33. 張栗粽,王謹平,劉貴松,羅光春&盧國明.（2018）.面向金融數據的神經網路時間序列預測模型.電腦應用研究（09）,2632-2637.
34. 張攀.（2021）.基於BP神經網路的金融不良債權回收率評估研究.中國資產評估（04）,36-40.doi:CNKI:SUN:ZCPG.0.2021-04-008.
35. 梁宏濤,劉碩,杜軍威,胡强,&於旭（2023）.深度學習應用於時序預測研究綜述.計算機科學與探索,1.
36. 梁循（2012）。支持向量機算法及其金融應用。北京：國家智慧財產權局知識產權出版社。
37. 淩銘,肖麗英,趙嘉,王萍根,王寅,項凱&蔡高堂.（2023）.基於SVM-CEEMDAN-BiLSTM模型的日降水量預測.人民珠江（09）,61-68.
38. 郭璿.（2022）.基於BP神經網路的科技企業信貸風險評估實證研究.陝西理工大學學報（社會科學版）（05）,65-71.doi:CNKI:SUN:HZSF.0.2022-05-010.
39. 陳偉,石仕華,陳華勇,袁偉倩,羅睿寧&楊莉.（2021）.基於BP神經網路的特殊客戶群體金融服務優化研究——以小微企業信用評級研究為例.區域金融研究（12）,51-56.doi:CNKI:SUN:GXJR.0.2021-12-007.
40. 陳强.(2021).機器學習及Python應用：高等教育出版社.
41. 雪,鮑剛&龔順琦.（2022）.基於參數優化的KELM和GRU的短期電力負荷預測.電子器件（04）,931-938.
42. 彭蘋.（2023）.基於R語言ARIMA模型和LSTM模型的中藥材價格指數預測.長江資訊通信（08）,26-28.
43. 程文輝&車文剛.（2022）.基於二次分解與LSTM的金融時間序列預測算法研究.重慶郵電大學學報（自然科學版）（04）,638-645.
44. 楊亞男.（2022）.關於股票市場預測建模研究（碩士學位論文,浙江科技學院）.https://kns.cnki.net/kcms2/article/abstract?v=innwydrwifl0oo4udqjyaki8ipojdnb-0YGGoj0ex_ESVhZZrD0TKDT2seOvpc8aQaxrTyCUx2cgC7gRK_QlRXIz16CyRfW9tWMGJEoXpaf30M0qQtjDV9HyRl5qqdVK&uniplatform=NZKPT&language=CHS
45. 遊皓麟.R語言預測實戰[M].北京：電子工業出版社,2017年第一版.
46. 熊思亦&熊永良.（2023）.基於CEEMDAN-LSTM組合方法的海平面變化預測分析.大地測量與地球動力學（09）,899-903.doi:10.14075/j.jgg.2023.09.004.
47. 管學英.（2024）.基於ARIMA-RNN混合模型的股價預測.哈爾濱商業大學學報（自然科學版）（02），250-256.doi:10.19492/j.cnki.1672-0946.2024.02.008.
48. 趙博宇.（2021）.機器學習在匯率預測中的組合研究（碩士學位論文,浙江大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202102&filename=1021626577.nh
49. 趙煜&韓旭昊.（2023）.基於CEEMDAN-LSTM組合的蘭州空氣品質指數預測.安徽師範大學學報（自然科學版）（05）,433-439+447.doi:10.14182/J.cnki.1001-2443.2023.05.004.
50. 趙煜&韓旭昊.（2023）.基於CEEMDAN-LSTM組合的蘭州空氣品質指數預測.安徽師範大學學報（自然科學版）（05），433-439+447.doi:10.14182/J.cnki.1001-2443.2023.05.004.
51. 劉揚&杜帥兵.（2023）.基於改進EMD-SSA-KELM的用水量預測方法研究.人民黃河（06）,73-78+85.
52. 劉磊.（2023）.投資者網絡情緒指數構建及其在股市指數預測建模中的應用研究（碩士學位論文,西北大學）.https://kns.cnki.net/kcms2/article/abstract?v=kiaz1sjia-71qqMIscF5uWePOomNM2W83VouNO_yHkTW0KGD3SPVCUcpedcTIiL61-Z67nwks5bMimDUyc1TGWI51XNwYTY72oiKm9iFp9oUrDRhe2tRLprUj_YKhR7KIptaZhSgJmM=&uniplatform=NZKPT&language=CHS
53. 劉穎,李惠迪&譚博元.（2022）.基於多源數據深度融合的金融時間序列預測.統計與決策（23）,52-56.doi:10.13546/j.cnki.tjyjc.2022.23.010.
54. 潘和平&張承釗.（2018）.FEPA-金融時間序列自我調整組合預測模型.中國管理科學（06）,26-38.doi:10.16381/j.cnki.issn1003-207x.2018.06.004.
55. 蔔鈺家.（2022）.基於GA-BP神經網路的成都市房價預測模型.現代電腦（20）,98-102.doi:CNKI:SUN:XDJS.0.2022-20-019.
56. 學峰張亞濤. （2021）.資本市場開放能够降低雜訊交易程度嗎？—— 基於滬港通的經驗證據.金融科學（02）,23-39.
57. 錢子傑.（2021）.基於ICEEMDAN-GWO-MKELM的金融時間序列預測（碩士學位論文,西南財經大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cmfd202202&filename=1021735972.nh
58. 錢吳永&張浩男.（2022）.基於Adaboost-DPSO-SVM模型的供應鏈金融信用風險評估研究.工業技術經濟（03）,72-79.doi:CNKI:SUN:GHZJ.0.2022-03-007.
59. 龍馬高新教育.（2018）.Python3資料分析與機器學習實戰-預測分析.InPython3資料分析與機器學習實戰（pp.165–168）.essay,北京大學出版社.
60. 薛薇.（2021）.Python機器學習原理與實踐-數據預測中的相關問題.InPython機器學習原理與實踐（pp.54–56）.essay,中國人民大學出版社.
61. 謝遊宇&王萬雄（2023）..基於EMD和SSA的股票預測模型.電腦工程與應用.
62. 韓志遠.（2023）.基於數據差分的LSTM模型庫存商品需求預測.中國儲運（09）,152-153.doi:10.16301/j.cnki.cn12-1204/f.2023.09.114.
63. 韓璐,蘇治&劉志東.（2020）.金融市場的協動預測模型：DWT-SVM方法.系統科學與數學（12）,2342-2356.
64. 叢敬奇,成鵬飛&趙振軍..基於CEEMD-CNN-LSTM的股票指數集成預測模型.系統工程.
65. 聶良剛&蘭瑞樂.（2023）.基於ICOA優化極限學習機的網安態勢預測.電腦工程與設計（04）,998-1006.doi:10.16208/j.issn1000-7024.2023.04.006.
66. 聶軼文&王韡. （2023）.基於PCA-GA-BP神經網路模型對安徽省物流需求量預測.阜陽師範大學學報（自然科學版）（04），96-102.doi:10.14096/j.cnki.cn34-1069/n/2096-9341（2023）04-0096-07.
67. 羅子幸. （2021）.雜訊交易對我國證券市場的影響研究.科技資訊（19）,190-192.doi:10.16661/j.cnki.1672-3791.2106-5042-2879.
68. 羅志丹.（2023）.數據驅動的金融時間序列混合預測模型研究與實證分析（博士學位論文,對外經濟貿易大學）.https://kns.cnki.net/kcms2/article/abstract?v=kiaz1sjia-5AUA7XvgQ8v9ZYnWjNYF_kZOps-VZ6l1A0yHBO83udWFdO8PeR-Jf2jhs2B8JsaWmfPJyvxd0MO3xPbANLcB2jbkH7Tu9XeliubNhv87tMSMUpsgY0ab1HsnpbrliH5II=&uniplatform=NZKPT&language=CHS
69. 蘇礦喜.（2022）.基於EMD去噪算法的股市投資組合研究（博士學位論文,華中師範大學）.https://kns.cnki.net/kcms/detail/detail.aspx?dbname=cdfdlast2023&filename=1022084394.nh
70. Bao,Y.,Lu,Y.,&Zhang,J.(2004).Forecasting stock price by SVMs regression.In Artificial Intelligence: Methodology, Systems, and Applications: 11th International Conference, AIMSA 2004, Varna, Bulgaria, September 2-4, 2004. Proceedings 11 (pp.295-303).Springer Berlin Heidelberg.
71. Belavadi, S. V., Rajagopal, S., Ranjani, R., & Mohan, R. (2020). Air quality forecasting using LSTM RNN and wireless sensor networks. Procedia Computer Science, 170, 241-248.
72. Black, F. (1986). Noise. The journal of finance, 41(3), 528-543.
73. Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of econometrics, 31(3), 307-327.
74. Bouktif, S., Fiaz, A., Ouni, A., & Serhani, M. A. (2020). Multi-sequence LSTM-RNN deep learning and metaheuristics for electric load forecasting. Energies, 13(2), 391.
75. Box,G.E.,Jenkins,G.M.,Reinsel,G.C.,&Ljung,G.M.(2015).Time series analysis: forecasting and control. JohnWiley&Sons.
76. Cameron, A. C., & Windmeijer, F. A. (1997). An R-squared measure of goodness of fit for some common nonlinear regression models. Journal of econometrics, 77(2), 329-342.
77. Cao, J., Li, Z., & Li, J. (2019). Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical mechanics and its applications, 519, 127-139.
78. Cao, L., & Tay, F. E. (2001). Financial forecasting using support vector machines. Neural Computing & Applications, 10, 184-192.
79. ChaiT, D. R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE). Arguments againstavoiding RMSEintheliterature, 7(1), 1247.
80. Chen, F., Chen, J., & Liu, J. (2022). Forecast of flood disaster emergency material demand based on IACO-BP algorithm. Neural Computing and Applications, 1-13.
81. Chen, Y., & Khong, E. (2022). A stacked forecasting model-CEEMDAN-BPMs model. Academic Journal of Computing & Information Science, 5(9), 82-89.
82. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297.
83. De Long, J. B., Shleifer, A., Summers, L. H., & Waldmann, R. J. (1990). Noise trader risk in financial markets. Journal of political Economy, 98(4), 703-738.
84. De Myttenaere, A., Golden, B., Le Grand, B., & Rossi, F. (2016). Mean absolute percentage error for regression models. Neurocomputing, 192, 38-48.
85. Dubois, D. J., Prade, H., & Yager, R. R. (Eds.). (2014). Readings in fuzzy sets for intelligent systems. Morgan Kaufmann.
86. Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica: Journal of the econometric society, 987-1007.
87. Engle, R. F., Lilien, D. M., & Robins, R. P. (1987). Estimating time varying risk premia in the term structure: The ARCH-M model. Econometrica: journal of the Econometric Society, 391-407.
88. Fan, J., & Yao, Q. (2003). Nonlinear time series: nonparametric and parametric methods (Vol. 20). New York: Springer.
89. Fang,T.,Zheng,C.,&Wang,D.(2023).Forecasting the crude oil prices with an EMD-ISBM-FNNmodel.Energy,263,125407.
90. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232.
91. Hecht-Nielsen, R. (1992). Theory of the backpropagation neural network. In Neural networks for perception (pp. 65-93). Academic Press.
92. Hochreiter,S.,&Schmidhuber,J.(1997).Long short-term memory. Neural computation, 9(8),1735-1780.
93. Huang, G. B., Zhou, H., Ding, X., & Zhang, R. (2011). Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 42(2), 513-529.
94. Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1-3), 489-501.
95. Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., ... & Liu, H. H. (1998). The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 454(1971), 903-995.
96. Huang,Y.,Yu,J.,Dai,X.,Huang,Z.,&Li,Y.(2022).Air-quality prediction based on the EMD–IPSO–LSTM combination model.Sustainability,14(9),4889.
97. Jamei, M., Ali, M., Malik, A., Karbasi, M., Rai, P., & Yaseen, Z. M. (2023). Development of a TVF-EMD-based multi-decomposition technique integrated with Encoder-Decoder-Bidirectional-LSTM for monthly rainfall forecasting. Journal of Hydrology, 617, 129105.
98. Khemakhem, S., & Boujelbene, Y. (2018). Predicting credit risk on the basis of financial and non-financial variables and data mining. Review of accounting and finance, 17(3), 316-340.
99. Liu, D., Liu, C., Fu, Q., Li, T., Imran, K. M., Cui, S., & Abrar, F. M. (2017). ELM evaluation model of regional groundwater quality based on the crow search algorithm. Ecological Indicators, 81, 302-314.
100.Liu, N., Tang, Q., Zhang, J., Fan, W., & Liu, J. (2014). A hybrid forecasting model with parameter optimization for short-term load forecasting of micro-grids. Applied Energy, 129, 336-345.
101.Liu, Y., Zhao, Q., Yao, W., Ma, X., Yao, Y., & Liu, L. (2019). Short-term rainfall forecast model based on the improved BP–NN algorithm. Scientific reports, 9(1), 19751.
102.Meng,D.,Wang,H.,Yang,S.,Lv,Z.,Hu,Z.,&Wang,Z.(2022).Fault analysis of wind power rolling bearing based on EMD feature extraction.CMES-Computer Modeling in Engineering & Sciences,130(1),543-558.
103.Meyer, D., & Wien, F. T. (2001). Support vector machines. R News, 1(3), 23-26.
104.N-BEATS-RNN: Deep learning for time series forecasting. In 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 765-768). IEEE.
105.Nelson, D. B. (1992). Filtering and forecasting with misspecified ARCH models I: Getting the right variance with the wrong model. Journal of econometrics, 52(1-2), 61-90.
106.Pan,H.(2011).A basic theory o fintelligent finance.New Mathematics and Natura lComputation,7(02),197-227.
107.Parida, N., Mishra, D., Das, K., & Rout, N. K. (2021). Development and performance evaluation of hybrid KELM models for forecasting of agro-commodity price. Evolutionary Intelligence, 14, 529-544.
108.Qin, J., Tao, Z., Huang, S., & Gupta, G. (2021, March). Stock price forecast based on ARIMA model and BP neural network model. In 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) (pp. 426-430). IEEE.
109.Sezer, O. B., Gudelek, M. U., & Ozbayoglu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied soft computing, 90, 106181.
110.Stein, J. C. (1996). Rational capital budgeting in an irrational world.
111.Tay, F. E., & Cao, L. (2001). Application of support vector machines in financial time series forecasting. omega, 29(4), 309-317.
112.Wang, R., Peng, C., Gao, J., Gao, Z., & Jiang, H. (2020). A dilated convolution network-based LSTM model for multi-step prediction of chaotic time series. Computational and Applied Mathematics, 39, 1-22.
113.Wang, Z., & Bovik, A. C. (2009). Mean squared error: Love it or leave it? A new look at signal fidelity measures. IEEE signal processing magazine, 26(1), 98-117.
114.Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, 30(1), 79-82.
115.Xu, Q., & Kong, W. (2021, July). Research on forecast model based on BP neural network algorithm. In Journal of Physics: Conference Series (Vol. 1982, No. 1, p. 012065). IOP Publishing.
116.Yang, R., Yu, L., Zhao, Y., Yu, H., Xu, G., Wu, Y., & Liu, Z. (2020). Big data analytics for financial Market volatility forecast based on support vector machine. International Journal of Information Management, 50, 452-462.
117.Yu, L., Chen, H., Wang, S., & Lai, K. K. (2008). Evolving least squares support vector machines for stock market trend mining. IEEE transactions on evolutionary computation, 13(1), 87-102.
118.Zhang, W., Qu, Z., Zhang, K., Mao, W., Ma, Y., & Fan, X. (2017). A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting. Energy conversion and management, 136, 439-451.
119.Zhang, Y. (2019). Application of improved BP neural network based on e-commerce supply chain network data in the forecast of aquatic product export volume. Cognitive Systems Research, 57, 228-235.
120.Zhang, Y., & Wang, Y. (2023). Forecasting crude oil futures market returns: A principal component analysis combination approach. International Journal of Forecasting, 39(2), 659-673.
121.Zhou, C., Yin, K., Cao, Y., Intrieri, E., Ahmed, B., & Catani, F. (2018). Displacement prediction of step-like landslide by applying a novel kernel extreme learning machine method. Landslides, 15, 2211-2225.
