Chaotic time series for copper’s price forecast: neural networks and the discovery of knowledge for big data

Abstract

We investigated the potential of Artificial Neural Networks (ANN), ANN to forecasts in chaotic series of the price of copper; based on different combinations of structure and possibilities of knowledge in big discovery data. Two neural network models were built to predict the price of copper of the London Metal Exchange (LME) with lots of 100 to 1000 data. We used the Feed Forward Neural Network (FFNN) algorithm and Cascade Forward Neural Network (CFNN) combining training, transfer and performance implemented functions in MatLab. The main findings support the use of the ANN in financial forecasts in series of copper prices. The copper price’s forecast using different batches size of data can be improved by changing the number of neurons, functions of transfer, and functions of performance s. In addition, a negative correlation of −0.79 was found in performance indicators using RMS and IA.