forecasting gold price changes: application of an equipped artificial neural network

The forecast of fluctuations of prices is the major concern in financial markets. thus, developing an accurate and robust forecasting decision model is critical for investors. as gold has shown a special capability to smooth inflation fluctuations, governors use gold as a price controlling lever. thus, more information about future gold price trends will help make the firm decisions. this paper attempts to propose an intelligent model founded by artificial neural networks (anns) to project future prices of gold. the proposed intelligent network is equipped with a meta-heuristic algorithm called bat algorithm to make ann capable of following fluctuations. the designed model is compared to that of a published scientific paper and other competitive models such as autoregressive integrated moving average (arima), ann, adaptive neuro-fuzzy inference system (anfis), multilayer perceptron (mlp) neural network, radial basis function (rbf) neural network and generalized regression neural networks (grnn). in order to evaluate model performance, root mean squared error (rmse) was employed as an error index. results show that the proposed bat-neural network (bnn) outperforms both conventional and modern forecasting models.