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.
Highlights
Copper is one of the basic metal products listed on major exchanges in the world: the London Metal Exchange (LME), Commodity Exchange of New York (COMEX) and Shanghai Futures Exchange (SHFE)
We found that Feed Forward Neural Network (FFNN) and Cascade Forward Neural Network (CFNN) for batches of 100 data obtained the best results with the training functions named traincgf, traincgb, and traincgp
Forecasts based on neural network, nonlinear models achieved better results compared with linear forecasting models
Summary
Copper is one of the basic metal products listed on major exchanges in the world: the LME, Commodity Exchange of New York (COMEX) and Shanghai Futures Exchange (SHFE). The price of copper is a sensitive issue for major producers such as Codelco, Freeport-McMoRan Copper & Gold, Glencore Xstrata, BHP Billiton, Southern Copper Corporation, American Smelting and Refining Company. Economies such as those of Chile and Zambia rely heavily on copper production and, subsequently, in the evolution of the prices of the same [2], being Chile the largest producer and exporter of the world. They employ a variety of different methods and mathematical models: time series [3–5],combined with wavelet [6, 7], transformed of Fourier [8], swarm optimisation algorithm [9], and models of multiproducts [10]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have