A feed-forward neural network approach to Istanbul Stock Exchange

Abstract

In this study the trend estimation of the participation indices (PARTI) in the Istanbul Stock Exchange (BIST) using artificial neural network (ANN) theory. PARTI can be regarded as the Participation 50 Index (KAT50) and the Participation 30 Index (KATLM). Since KAT50 has only been calculated since 9th July 2014, there are only a few studies on this index. On the other hand, PARTI indices are growing more and more important in global economies, especially in Turkey, England, etc. Therefore, in this study, firstly, we have used ANN method, using 1410 daily closing values of KATLM, between 1st August 2012 and 30th June 2016. For the KAT50 index, we used 720 daily closing values between 9th July 2014 and 29th July 2016. We created a feed-forward back-propagation neural network model in order to predict the trends of these indices and we applied the previously mentioned daily closing values of these participation indices to this model. The results obtained using the ANN method are compared in the figures and tables. It can be concluded that the results of this study are very helpful for individual and institutional investors’ investment decisions within global economies.