EUVIMEDEUVIMED entdecken
Crossref

A COMPARISION OF NEURAL NETWORK AND LINEAR REGRESSION FORECASTS OF THE ISE-100 INDEX

Murat ÇİNKO, Emin AVCI

Öneri Dergisi · 05.02.2020 · 301-307

DOI: 10.14783/maruoneri.684425 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Öneri Dergisi, online erschienen am 05.02.2020. Verfasst von Murat ÇİNKO und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years the artificial neural network models have been successfully applied to solve many the real life problems. Especially for the last decade, the artificial neural network models have been applied to solve financial problems like bankruptcy prediction, portfolio construction, credit assessments and stock market forecasting. This study examines the comparison of artificial neural network models and stepwise linear regression forecasting the daily and sessional returns of the ISE-100 index. By using stepwise regression inputs is selected tlien the same inputs is used in the neural network. Both methods are compared on the basis of mean squared error, normalized mean squared error and trend accuracy measures. Relying the findings of this study, it is concluded that the artificial neural network model is better than stepwise linear regression.

Zitieren

APA

ÇİNKO, M., & AVCI, E. (2020). A COMPARISION OF NEURAL NETWORK AND LINEAR REGRESSION FORECASTS OF THE ISE-100 INDEX. Öneri Dergisi, 301-307. https://doi.org/10.14783/maruoneri.684425

Vancouver

ÇİNKO M, AVCI E. A COMPARISION OF NEURAL NETWORK AND LINEAR REGRESSION FORECASTS OF THE ISE-100 INDEX. Öneri Dergisi. 2020:301-307. doi:10.14783/maruoneri.684425

BibTeX
@article{NKO2020,
  author = {ÇİNKO, Murat and AVCI, Emin},
  title = {A COMPARISION OF NEURAL NETWORK AND LINEAR REGRESSION FORECASTS OF THE ISE-100 INDEX},
  journal = {Öneri Dergisi},
  year = {2020},
  pages = {301--307},
  doi = {10.14783/maruoneri.684425}
}
Kostenlos starten →