基于AdaBoost-AAFSA-Elman模型及CEEMDAN算法的股市网络舆情收盘价预测

doi:10.1007/s12204-021-2337-x

摘要/Abstract

摘要： 针对Elman神经网络算法在股市收盘价格预测中预测精度低的问题, 基于自适应噪声的完全集合经验模态分解（CEEMDAN），提出了自适应boosting（AdaBoost）算法与人工鱼群优化改进算法（AAFSA）以及 Elman神经网络的组合预测模型。CEEMDAN算法通过对Boruta算法和文本挖掘算法获得的属性集添加白噪声，实现属性序列的分解与降噪；同时利用自适应步长和视角范围对AFSA算法进行了改进，并利用改进后的AAFSA算法优化Elman算法的权值和阈值；最后利用AdaBoos算法在连续迭代的过程中将5个AAFSA-Elman弱预测器组成一个强预测器，从而提高了预测的精度。实验表明：相比 Elman神经网络，AdaBoost-AAFSA-Elman模型的平均绝对百分比误差（MAPE）从4.9423%降低到1.2338%。本研究提出的模型为基于网络舆论股票收盘价格预测提供了一种实验方法。

关键词: 股市网络舆情，CEEMDAN算法，AdaBoost算法，AFSA算法，Elman神经网络

Abstract: To solve low prediction accuracy of Elman in predicting stock closing price, the model of adaptive boosting (AdaBoost)-improved artificial fish swarm algorithm (AAFSA)-Elman based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is proposed. By adding different white noise to the original data, CEEMDAN algorithm is used to decompose attributes serial selected by Boruta algorithm and text mining. To optimize the weight and threshold of Elman, self-adaption step length and view scope are used to improve artificial fish swarm algorithm (AFSA). AdaBoost algorithm is used to compose 5 weak AAFSA-Elman predictors into a strong predictor by continuous iteration. Experiments show that the mean absolute percentage error (MAPE) of AdaBoost-AAFSA-Elman model reduces from 4.9423% to 1.2338%. This study provides an experimental method for the prediction of stock closing price based on network public opinio.

Key words: network public opinion, CEEMDAN, AdaBoost, AFSA, Elman

中图分类号:

TP391

朱昶胜1，康亮河1,3，冯文芳2. 基于AdaBoost-AAFSA-Elman模型及CEEMDAN算法的股市网络舆情收盘价预测[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(6): 809-821.

ZHU Changsheng1 (朱昶胜)，KANG Lianghe1.3* (康亮河)，FENG Wenfang2 (冯文芳). Predicting Stock Closing Price with Stock Network Public Opinion Based on AdaBoost-AAFSA-Elman Model and CEEMDAN Algorithm[J]. J Shanghai Jiaotong Univ Sci, 2023, 28(6): 809-821.

参考文献 30

[11]	RENAULT T. Intraday online investor sentiment and return patterns in the US stock market [J]. Journal of Banking & Finance, 2017, 84: 25-40.
[1]	SAGGI M K, JAIN S. A survey towards an integration of big data analytics to big insights for valuecreation [J]. Information Processing & Management, 2018, 54(5): 758-790.
[12]	XIONG T, BAO Y K, HU Z Y. Multiple-output support vector regression with a firefly algorithm for interval-valued stock price index forecasting [J]. Knowledge-Based Systems, 2014, 55: 87-100.
[2]	EL OUADGHIRI I, PEILLEX J. Public attention to “Islamic terrorism” and stock market returns [J]. Journal of Comparative Economics, 2018, 46(4): 936- 946.
[13]	KAO L J, CHIU C C, LU C J, et al. A hybrid approach by integrating wavelet-based feature extraction with MARS and SVR for stock index forecasting [J]. Decision Support Systems, 2013, 54(3): 1228-1244.
[3]	CHAN J, LIN S, YU Y, et al. Analysts’ stock ownership and stock recommendations [J]. Journal of Accounting and Economics, 2018, 66(2/3): 476- 498.
[14]	LI S W, CHEN T, WANG L, et al. Effective tourist volume forecasting supported by PCA and improved BPNN using Baidu index [J]. Tourism Management, 2018, 68: 116-126.
[4]	DU P, WANG J Z, YANG W D, et al. Multi-step ahead forecasting in electrical power system using a hybrid forecasting system [J]. Renewable Energy, 2018, 122: 533-550.
[15]	YOU D, CHEN F. Research on the prediction of network public opinion based on improved PSO and BP neural network [J]. Journal of Intelligence, 2016, 35(8): 156-161 (in Chinese).
[5]	LIU J, MA F, ZHANG Y J. Forecasting the Chinese stock volatility across global stock markets [J]. Physica A: Statistical Mechanics and Its Applications, 2019, 525: 466-477.[6] DAI Z F, ZHOU H T, WEN F H, et al. Efficient predictability of stock return volatility: The role of stock market implied volatility [J]. The North American Journal of Economics and Finance, 2020, 52: 101174.
[16]	DASH S R, MAITRA D. Does sentiment matter for stock returns? Evidence from Indian stock market using wavelet approach [J]. Finance Research Letters, 2018, 26: 32-39.
[7]	DRURY B, ROCHE M. A survey of the applications of text mining for agriculture [J]. Computers and Electronics in Agriculture, 2019, 163: 104864.
[17]	XIAO C J, CHEN N C, HU C L, et al. Short and midterm sea surface temperature prediction using timeseries satellite data and LSTM-AdaBoost combination approach [J]. Remote Sensing of Environment, 2019, 233: 111358.
[8]	ABOUNOORI E, TOUR M. Stock market interactions among Iran, USA, Turkey, and UAE [J]. Physica A: Statistical Mechanics and Its Applications, 2019, 524: 297-305.
[18]	XU M J, SHANG P J, LIN A J. Cross-correlation analysis of stock markets using EMD and EEMD [J]. Physica A: Statistical Mechanics and Its Applications, 2016, 442: 82-90.
[9]	ZHANG G, XU L, XUE Y. Model and forecast stock market behavior integrating investor sentiment analysis and transaction data [J]. Cluster Computing, 2017, 20(1): 789-803.
[19]	SHARMA S S, THURAISAMY K, MADYAN M, et al. Evidence of price discovery on the Indonesian stock exchange [J]. Economic Modelling, 2019, 83: 2-7.
[10]	BROWN G W, CLIFF M T. Investor sentiment and the near-term stock market [J]. Journal of Empirical Finance, 2004, 11(1): 1-27.
[20]	FANG Y. Feature selection, deep neural network and trend prediction [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(2): 297-307.
[11]	RENAULT T. Intraday online investor sentiment and return patterns in the US stock market [J]. Journal of Banking & Finance, 2017, 84: 25-40.
[21]	SPIRO A G, GOL’DOVSKAYA M D, KISELEVA N E, et al. Segmentation and hashing of time series in stock market prediction [J]. Automation and Remote Control, 2018, 79(5): 911-918.
[12]	XIONG T, BAO Y K, HU Z Y. Multiple-output support vector regression with a firefly algorithm for interval-valued stock price index forecasting [J]. Knowledge-Based Systems, 2014, 55: 87-100.
[22]	ZHANG W, LIN S, ZHANG Y J. Intraday marketwide ups/Downs and returns [J]. Journal of Management Science and Engineering, 2016, 1(1): 28-57.
[13]	KAO L J, CHIU C C, LU C J, et al. A hybrid approach by integrating wavelet-based feature extraction with MARS and SVR for stock index forecasting [J]. Decision Support Systems, 2013, 54(3): 1228-1244.
[23]	ARROYO-FERN′ ANDEZ I, M′ ENDEZ-CRUZ C F, SIERRA G, et al. Unsupervised sentence representations as word information series: Revisiting TF-IDF [J]. Computer Speech & Language, 2019, 56: 107-129.
[14]	LI S W, CHEN T, WANG L, et al. Effective tourist volume forecasting supported by PCA and improved BPNN using Baidu index [J]. Tourism Management, 2018, 68: 116-126.
[24]	CAO J, LI Z, LI J. Financial time series forecasting model based on CEEMDAN and LSTM [J]. Physica A: Statistical Mechanics and Its Applications, 2019, 519: 127-139.
[15]	YOU D, CHEN F. Research on the prediction of network public opinion based on improved PSO and BP neural network [J]. Journal of Intelligence, 2016, 35(8): 156-161 (in Chinese).
[25]	ZHOU Z B, LIN L, LI S X. International stock market contagion: A CEEMDAN wavelet analysis [J]. Economic Modelling, 2018, 72: 333-352.
[16]	DASH S R, MAITRA D. Does sentiment matter for stock returns? Evidence from Indian stock market using wavelet approach [J]. Finance Research Letters, 2018, 26: 32-39.
[26]	CHENG Z, LU Z X. Research on the PID control of the ESP system of tractor based on improved AFSA and improved SA [J]. Computers and Electronics in Agriculture, 2018, 148: 142-147.
[17]	XIAO C J, CHEN N C, HU C L, et al. Short and midterm sea surface temperature prediction using timeseries satellite data and LSTM-AdaBoost combination approach [J]. Remote Sensing of Environment, 2019, 233: 111358.
[27]	LI J P, DONG P W. Global maximum power point tracking for solar power systems using the hybrid artificial fish swarm algorithm [J]. Global Energy Interconnection, 2019, 2(4): 351-360.
[18]	XU M J, SHANG P J, LIN A J. Cross-correlation analysis of stock markets using EMD and EEMD [J]. Physica A: Statistical Mechanics and Its Applications, 2016, 442: 82-90.
[28]	WANG Y L. Stock market forecasting with financial micro-blog based on sentiment and time series analysis [J]. Journal of Shanghai Jiao Tong University (Science), 2017, 22(2): 173-179.
[19]	SHARMA S S, THURAISAMY K, MADYAN M, et al. Evidence of price discovery on the Indonesian stock exchange [J]. Economic Modelling, 2019, 83: 2-7.
[29]	OWUSU E, ZHAN Y Z, MAO Q R. A neuralAdaBoost based facial expression recognition system [J]. Expert Systems With Applications, 2014, 41(7): 3383-3390.
[20]	FANG Y. Feature selection, deep neural network and trend prediction [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(2): 297-307.
[30]	YUAN G H, YANG W X. Study on optimization of economic dispatching of electric power system based on Hybrid Intelligent Algorithms (PSO and AFSA) [J]. Energy, 2019, 183: 926-935.
[21]	SPIRO A G, GOL’DOVSKAYA M D, KISELEVA N E, et al. Segmentation and hashing of time series in stock market prediction [J]. Automation and Remote Control, 2018, 79(5): 911-918.
[22]	ZHANG W, LIN S, ZHANG Y J. Intraday marketwide ups/Downs and returns [J]. Journal of Management Science and Engineering, 2016, 1(1): 28-57.
[23]	ARROYO-FERN′ ANDEZ I, M′ ENDEZ-CRUZ C F, SIERRA G, et al. Unsupervised sentence representations as word information series: Revisiting TF-IDF [J]. Computer Speech & Language, 2019, 56: 107-129.
[24]	CAO J, LI Z, LI J. Financial time series forecasting model based on CEEMDAN and LSTM [J]. Physica A: Statistical Mechanics and Its Applications, 2019, 519: 127-139.
[25]	ZHOU Z B, LIN L, LI S X. International stock market contagion: A CEEMDAN wavelet analysis [J]. Economic Modelling, 2018, 72: 333-352.
[26]	CHENG Z, LU Z X. Research on the PID control of the ESP system of tractor based on improved AFSA and improved SA [J]. Computers and Electronics in Agriculture, 2018, 148: 142-147.
[27]	LI J P, DONG P W. Global maximum power point tracking for solar power systems using the hybrid artificial fish swarm algorithm [J]. Global Energy Interconnection, 2019, 2(4): 351-360.
[28]	WANG Y L. Stock market forecasting with financial micro-blog based on sentiment and time series analysis [J]. Journal of Shanghai Jiao Tong University (Science), 2017, 22(2): 173-179.
[29]	OWUSU E, ZHAN Y Z, MAO Q R. A neuralAdaBoost based facial expression recognition system [J]. Expert Systems With Applications, 2014, 41(7): 3383-3390.
[30]	YUAN G H, YANG W X. Study on optimization of economic dispatching of electric power system based on Hybrid Intelligent Algorithms (PSO and AFSA) [J]. Energy, 2019, 183: 926-935.