Abstract:

The uncertainty of the financial time series, along with chaotic movements, the nonlinear dynamic structure, makes forecasts quite stronger. The influence of many macroeconomic factors, such as political changes, the overall view of the economy, investors’ expectations and investment preferences, and the movements of other indicators, makes the index forecasts quite difficult but so attractive. It is known that machine learning algorithms are successful in producing stock index movements and future forecasts. This study addressed the problem of predicting the direction of the BIST 100 index movements. Three different machine learning algorithms have been used by artificial nerve networks, support vector machines and naive Bayes classification algorithms and performance compared. The stock exchange index is used as a input for the ten technical indicator models used for forecasts. The data set contains daily closing values covering the period 2009-2018. The results of the analysis showed that both three models could be used to capture stock index movements, while the artificial nerve network algorithm was a better classifier.

Keywords:

Abstract:

In addition to the uncertainty and chaotic movements of the financial time series, the nonlinear dynamic structure makes the forecasts very difficult. The fact that the stock market index are affected by the political changes, the general outlook of the economy, the investors' expectations and investment preferences, and the movements of other indexes, make the index estimates quite difficult but attractive. It is known that the machine learning algorithms are successful in estimating stock index movements and their future values. In this study, the problem of forecasting the direction of BIST 100 index movements is discussed. Three different machine learning algorithms, artificial neural networks, support vector machines and naïve Bayes classifier were used and their performances were compared. Ten technical indicators were used as inputs for the models. The data set consists of ten-year daily closing price values covering the 2009-2018 period. Analysis results show that the models can be used to capture stock market index movements, whereas artificial neural network algorithm is a better classifier.