Joshi, Devendra and Chithaluru, Premkumar and Anand, Divya and Hajjej, Fahima and Aggarwal, Kapil and Yélamos Torres, Vanessa and Bautista Thompson, Ernesto UNSPECIFIED, UNSPECIFIED, divya.anand@uneatlantico.es, UNSPECIFIED, UNSPECIFIED, vanessa.yelamos@funiber.org, ernesto.bautista@unini.edu.mx (2023) An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices. Mathematics, 11 (7). p. 1675. ISSN 2227-7390
|
Text
mathematics-11-01675-v2.pdf Available under License Creative Commons Attribution. Download (2MB) | Preview |
Abstract
In this research, a neural network (NN) model for metal price forecasting based on an evolutionary approach is proposed. Both the neural network model’s network parameters and network architecture are selected automatically. The time series metal price data set is used to construct a novel fitness function that takes into account both error minimizations and the reproduction of the auto-correlation function. Calculating the average entropy values allowed the selection of the input parameter count for the neural network model. Gold price forecasting was performed using the proposed methodology. The optimal hidden node number, learning rate, and momentum are 9, 0.026, and 0.76, respectively, according to the evolutionary-based NN model. The proposed strategy is shown to reduce estimation error while also reproducing the auto-correlation function of the time series data set by the validation results with gold price data. The performance of the proposed method is better than other current methods, according to a comparison study.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | evolutionary algorithm; auto-correlation; metal price; neural network; cross-validation; entropy |
| Subjects: | Subjects > Engineering |
| Divisions: | Europe University of Atlantic > Research > Scientific Production |
| Depositing User: | Sr Bibliotecario |
| Date Deposited: | 17 Oct 2023 14:33 |
| Last Modified: | 17 Oct 2023 14:33 |
| URI: | http://repositorio.funiber.org/id/eprint/9236 |
Actions (login required)
 |
View Item |
