Stock price forecasting model based on modified convolution neural network and financial time series analysis

Jiasheng Cao; Jinghan Wang

doi:10.1002/dac.3987

journal article May 29, 2019

Stock price forecasting model based on modified convolution neural network and financial time series analysis

Jiasheng Cao

Jinghan Wang

International Journal of Communication Systems Vol. 32 No. 12 · Wiley

View at Publisher Save 10.1002/dac.3987

Abstract

SummaryTo forecast the future trend of financial activities through its rules, a convolutional neural network (CNN) is used to forecast stock index. Firstly, a CNN stock index prediction model is constructed, the structural parameter relationship of the CNN model is analyzed, and a CNN model algorithm is implemented. Secondly, the influence of model parameters on prediction results is discussed, and the stock index prediction model based on CNN‐support vector machine (SVM) is established. At last, the empirical analysis is made, and the results show that the two prediction models are feasible and effective. It is concluded that the use of neural networks for financial prediction can deal with the continuous and categorical prediction variables and obtain good prediction results.

Topics

No keywords indexed for this article. Browse by subject →

References

42

[1]

10.1016/j.jempfin.2017.03.003

[2]

Bhandari A "The impact of executive inside debt on sell‐side financial analyst forecast characteristics" Rev Quant Finan Acc (2018)

[3]

Demerens F "The use of segment information by financial analysts and forecast accuracy: a study on European intermediate‐size companies" Thunderbird Int Bus Rev (2016)

[4]

10.1097/meg.0000000000000771

[5]

Kim H "Improving forecast accuracy of financial vulnerability: partial least squares factor model approach" Work Pap (2017)

[6]

10.15807/jorsj.45.373

[7]

Wen‐Ze W "Research on financial revenue forecast based on holt‐winter methods" J Hubei Norm Univ (2018)

[8]

Fedyk T "Refining financial analysts' forecasts by predicting earnings forecast errors" Soc Sci Electron Publ (2017)

[9]

10.1007/s41109-017-0028-1

[10]

10.1016/j.jcae.2017.05.001

[11]

10.3390/su10103765

[12]

10.1016/j.eswa.2017.10.023

[13]

10.1016/j.procs.2018.01.111

[14]

Wang SH "Sensorineural hearing loss identification via nine‐layer convolutional neural network with batch normalization and dropout" Multimed Tools Appl (2018)

[15]

10.3390/en11092292

[16]

Bai Y "A comparison of dimension reduction techniques for support vector machine modeling of multi‐parameter manufacturing quality prediction" J Intell Manuf (2018)

[17]

10.1111/idj.12326

[18]

10.1504/ijbic.2018.092808

[19]

Thanh Noi P "Comparison of random forest, k‐nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel‐2 imagery" Sensors (2018) 10.3390/s18010018

[20]

Kumar PJ "Support vector machine based retinal therapeutic for glaucoma using machine learning algorithm" Int J Med Eng Informat (2018)

[21]

You SD "Comparative study of singing voice detection based on deep neural networks and ensemble learning" HCIS (2018)

[22]

Khoobjou E "On hybrid intelligence‐based control approach with its application to flexible robot system" HCIS (2017)

[23]

Singh J "Optimization of sentiment analysis using machine learning classifiers" HCIS (2017)

[24]

Alireza S "Personality classification based on profiles of social networks' users and the five‐factor model of personality" HCIS (2018)

[25]

Iam‐On N "Generating descriptive model for student dropout: a review of clustering approach" HCIS (2017)

[26]

10.1186/s13673-018-0140-y

[27]

Vilakone P "An efficient movie recommendation algorithm based on improved k‐clique" HCIS (2018)

[28]

Zouina M "A novel lightweight URL phishing detection system using SVM and similarity index" Hindawi Limited (2017)

[29]

Rao M "Tracking intruder ship in wireless environment" Hindawi Limited (2017)

[30]

Song W "Classifying 3d objects in lidar point clouds with a back‐propagation neural network" HCIS (2018)

[31]

10.1016/j.ejor.2017.12.001

[32]

10.1016/j.jocs.2017.11.006

[33]

Song Y "DeepAct: a deep neural network model for activity detection in untrimmed videos" J Inf Process Syst (2018)

[34]

Zeng H "Convolutional neural network based multi‐feature fusion for non‐rigid 3D model retrieval" J Inf Process Syst (2018)

[35]

Lee S‐G "Variations of AlexNet and GoogLeNet to improve Korean character recognition performance" J Inf Process Syst (2018)

[36]

Lotfi A "Cross‐validation probabilistic neural network based face identification" J Inf Process Syst (2018)

[37]

Lee S "Video captioning with visual and semantic features" J Inf Process Syst (2018)

[38]

Li C "A multi‐scale parallel convolutional neural network based intelligent human identification using face information" J Inf Process Syst (2018)

[39]

Cao K "CNN‐LSTM coupled model for prediction of waterworks operation data" J Inf Process Syst (2018)

[40]

Kumar S "Detection of microcalcification using the wavelet based adaptive sigmoid function and neural network" J Inf Process Syst (2017)

[41]

Li* D "Wireless channel identification algorithm based on feature extraction and BP neural network" J Inf Process Syst (2017)

[42]

Teldja Amghar Y "A hybrid bacterial foraging optimization algorithm and a radial basic function network for image classification" J Inf Process Syst (2017)

Cited By

94

Machine learning techniques and data for stock market forecasting: A literature review

Mahinda Mailagaha Kumbure, Christoph Lohrmann · 2022

Expert Systems with Applications

Metrics

94

Citations

42

References

Details

Published: May 29, 2019
Vol/Issue: 32(12)
License: View

Authors

J

Jiasheng Cao

University of Science and Technology of China Hefei China

J

Jinghan Wang

Illinois Institute of Technology Chicago Illinois

Cite This Article

Jiasheng Cao, Jinghan Wang (2019). Stock price forecasting model based on modified convolution neural network and financial time series analysis. International Journal of Communication Systems, 32(12). https://doi.org/10.1002/dac.3987

Stock price forecasting model based on modified convolution neural network and financial time series analysis

You May Also Like