PREDICTION OF DAILY GOLD PRICE RETURNS WITH ARTIFICIAL NEURAL NETWORKS AND MARKOV CHAINS MODELS

During the last decade, there have been many studies on the prediction of gold prices. Artificial neural networks algorithm and Markov chains models perform fairly well in the prediction of gold prices. In this study, the daily returns of gold prices were estimated by using the powerful aspects of the artificial neural network algorithm and the Markov chains models. The prediction was made in two stages. In the first stage, the daily return series of gold prices were estimated by the artificial neural network algorithm which has the best prediction performance. In the second stage, the transition probabilities matrixes of high order Markov chains models were calculated from the estimated values that obtained from the artificial neural networks. The third order and the fourth order Markov chains models and the artificial neural networks algorithm were used jointly for prediction. In consequence of the applied methodology, about 70% success of prediction was achieved in the future prediction of the gold prices’ returns