Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

24.02.2020 | Focus | Ausgabe 11/2020

Soft Computing 11/2020

Prediction research of financial time series based on deep learning

Zeitschrift:
Soft Computing > Ausgabe 11/2020
Autoren:
Zhaoyi Xu, Jia Zhang, Junyao Wang, Zhiming Xu
Wichtige Hinweise
Communicated by Mu-Yen Chen.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Abstract

Currently, the world economics develops rapidly, and the finance business also develops promptly. As there are more financial activities, the uncertainty of change trend in financial activities is also increased constantly. How to study and grasp the laws of banking activity and calculate their coming tendency has grown into the concentrate and major study substance of scientific and monetary ring. On the one hand, available finance prediction can supply base for making finance plans and relevant decisions, thus ensuring the laudable expansion of the finance market and maximizing the benefits of profit organizations. However, on the other hand, convolution neural network (CNN) is a multilayer neural network composition that can simulate the operation machine-made of biological field system, which can be used to obtain effective feature description. Meanwhile, the features are extracted from the original data. Now, CNN has turned into a study hot point in the fields of giving a lecture discriminate, figure distinguishing, and classifying, and natural language handling. Moreover, it is widely used in these fields, and its application effect has been recognized by most people. Consequently, CNN composition is adopted to predict the finance time succession data. Firstly, the research means of financial time series are summarized, and then, the artificial neural network (ANN) and deep learning methods are briefly introduced. Afterward, the prediction model of stock index according to CNN model is proposed, and the influences of historical factors on model are analyzed. Finally, a few stock indexes are predicted to verify validity and effectiveness of the proposed CNN model through experimental comparison. And a hybrid model combined with CNN is found, thus further improving the cable CNN network model.

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 69.000 Bücher
  • über 500 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 58.000 Bücher
  • über 300 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 50.000 Bücher
  • über 380 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Maschinenbau + Werkstoffe




Testen Sie jetzt 30 Tage kostenlos.

Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 11/2020

Soft Computing 11/2020 Zur Ausgabe

Premium Partner

    Bildnachweise