Record Details

Predicting the Istanbul Stock Exchange Index Return using Technical Indicators: A Comparative Study

International Journal of Finance & Banking Studies

View Archive Info
 
 
Field Value
 
Title Predicting the Istanbul Stock Exchange Index Return using Technical Indicators: A Comparative Study
 
Creator Emir, Şenol; Beykent Üniversity
 
Subject —
Support Vector Regression; Linear Regression; index return prediction, technical indicators; symmetric and asymmetric metrics
 
Description Theaim of this study to examine the performance of Support Vector Regression (SVR)which is a novel regression method based on Support Vector Machines (SVM)approach in predicting the Istanbul Stock Exchange (ISE) National 100 Index dailyreturns. For bechmarking, results given by SVR were compared to those given byclassical Linear Regression (LR). Dataset contains 6 technical indicators whichwere selected as model inputs for 2005-2011 period. Grid search and crossvaliadation is used for finding optimal model parameters and evaluating themodels. Comparisons were made based on Root Mean Square (RMSE), Mean AbsoluteError (MAE), Mean Absolute Percentage Error (MAPE), Theil InequalityCoefficient (TIC) and Mean Mixed Error (MME) metrics. Results indicate that SVRoutperforms the LR for all metrics.
 
Publisher SSBFNET
 
Contributor —
 
Date 2013-07-26
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article
 
Format application/pdf
 
Identifier http://www.ssbfnet.com/ojs/index.php/ijfbs/article/view/191
 
Source International Journal of Finance & Banking Studies (ISSN: 2147- 4486); Vol 2, No 3 (2013): July; 111-117
2147-4486
 
Language eng
 
Relation http://www.ssbfnet.com/ojs/index.php/ijfbs/article/view/191/368