Predicting the Turkish Stock Market BIST 30 Index using Deep Learning
[ X ]
Date
2019
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Kırıkkale Üniversitesi
Access Rights
info:eu-repo/semantics/openAccess
Abstract
The non-linearity and high change rates of stockmarket index prices make prediction a challenging problem for traders and datascientists. Data modeling and machine learning have been extensively utilizedfor proposing solutions to this difficult problem. In recent years, deeplearning has proved itself in solving such complex problems. In this paper, we tacklethe problem of forecasting the Turkish Stock Market BIST 30 indexmovements and prices. We propose a deep learning model fed withtechnical indicators and oscillators calculated from historical index pricedata. Experiments conducted by applying our model on a dataset gathered for aperiod of 27 months on www.investing.com demonstrate that our solutionoutperforms other similar proposals and attains good accuracy, achieving 0.0332,0.109, 0.09, 0.1069 and 0.2581 as mean squared error in predicting BIST 30index prices for the next five trading days. Based on these results, we arguethat using deep neural networks is advisable for stock market index prediction.
Description
Keywords
Stock market index prediction, Deep learning, Deep Neural Network, Stock index, BIST
Journal or Series
Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi
WoS Q Value
Scopus Q Value
Volume
1
Issue
1-253
