THE USEFULNESS OF ENSEMBLE REGRESSION AND FEATURE SELECTION METHODS IN PREDICTING STOCK RETURNS

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

SETAYESH MOHAMMAD HOSSEIN; KAZEMNEZHAD MOSTAFA

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: The Financial Accounting and Auditing Researches Year:2017 | Volume:8 | Issue:32 Page(s): 1-28

Download Full-Text

Persian Verion

View:

1,299

Download:

Cites:

Information Journal Paper

Title

THE USEFULNESS OF ENSEMBLE REGRESSION AND FEATURE SELECTION METHODS IN PREDICTING STOCK RETURNS

Author(s)

SETAYESH MOHAMMAD HOSSEIN | KAZEMNEZHAD MOSTAFA | Issue Writer Certificate

Keywords

STOCK RETURNS PREDICTIONQ1

ENSEMBLE REGRESSIONQ2

FEATURE SELECTION METHODSQ2

Abstract

Present study investigates the usefulness of ENSEMBLE REGRESSION and FEATURE SELECTION METHODS (including correlation-based feature selection and Relief) in predicting stock returns of companies listed on Tehran Stock Exchange. For performance evaluation of ENSEMBLE REGRESSION, evaluation criteria (including mean absolute percentage error, root mean squared error and coefficient of determination) of this method compared with linear regression and artificial neural networks. Also, for performance evaluation of FEATURE SELECTION METHODS, evaluation criteria of these methods compared with using all variables. The experimental results of investigating 101 companies listed in Tehran Stock Exchange in 2004-2013 indicate that ENSEMBLE REGRESSION outperforms the linear regression and artificial neural networks. Furthermore, the results show that selected variables with correlation-based feature selection and Relief result in better prediction in compare with using all variables.

Cites

No record.

References

Cite

APA: Copy

SETAYESH, MOHAMMAD HOSSEIN, & KAZEMNEZHAD, MOSTAFA. (2017). THE USEFULNESS OF ENSEMBLE REGRESSION AND FEATURE SELECTION METHODS IN PREDICTING STOCK RETURNS. THE FINANCIAL ACCOUNTING AND AUDITING RESEARCHES, 8(32 ), 1-28. SID. https://sid.ir/paper/197918/en

Vancouver: Copy

SETAYESH MOHAMMAD HOSSEIN, KAZEMNEZHAD MOSTAFA. THE USEFULNESS OF ENSEMBLE REGRESSION AND FEATURE SELECTION METHODS IN PREDICTING STOCK RETURNS. THE FINANCIAL ACCOUNTING AND AUDITING RESEARCHES[Internet]. 2017;8(32 ):1-28. Available from: https://sid.ir/paper/197918/en

IEEE: Copy

MOHAMMAD HOSSEIN SETAYESH, and MOSTAFA KAZEMNEZHAD, “THE USEFULNESS OF ENSEMBLE REGRESSION AND FEATURE SELECTION METHODS IN PREDICTING STOCK RETURNS,” THE FINANCIAL ACCOUNTING AND AUDITING RESEARCHES, vol. 8, no. 32 , pp. 1–28, 2017, [Online]. Available: https://sid.ir/paper/197918/en

Related Journal Papers