Baltic stock market prediction by using NARX

Forecasting the returns of stock markets is gaining importance nowadays in finance. For this aim, in the last decade, Artificial Neural Networks (ANN) have been widely used to forecast stock market movements. In Baltic countries, artificial neural networks are not commonly used in predicting financial failures. This study aims using artificial neural networks to predict OMX Baltic Benchmark GI (OMXBBGI) market index value. The lack of studies to forecast the Baltic Market index values is the main reason for this study. This study uses the nonlinear autoregressive network with exogenous inputs (NARX) to forecast values of OMX index. The research performed on the Baltic stock market uses index value and EUR/USD exchange rate to predict the index. After the inputs have been defined, the data have been gathered for the period of January 1, 2013, through January 01, 2017 from http://www.nasdaqbaltic.com. The training set is determined to include about 70% of the data set, and 15% will be used for testing, and the rest of 15% will be used for validation purposes. Matlab ANN tool is used to complete the tests. The results showed that Baltic Market values are successfully predicted by NARX methodology with the variables: Exchange rate and previous days' index values. The uniqueness of the paper especially comes from variables that have never been tried to forecast Baltic Stock Market values by ANN.