94-108
Forecasting the Price Index Return and Movement Direction using Data Mining Techniques
Authors: Günter Şenyurt, Abdülhamit Subaşı
Number of views: 559
Even though many new data mining techniques have been introduced in prediction estimation, there is still no single best solution to all financial problems. In this study, the performances of data mining techniques based on the daily Istanbul Stock Exchange (ISE) Index are examined and compared. The linear regression model, simple logistic (classification), artificial neural networks (ANN) and support vector machines (SVM) models are utilized in two ways, one for classification of market movements and the other for predicting price index returns through regression. Ten technical market indicators, 7 macroeconomic variables, a couple of other international market indices and a sliding window of ten inputs make up the 30 attributes used in this study. Different combinations of attribute sets are experimented with different ANN and SVM model parameter values to find the highest forecasting accuracy.