An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices
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 f...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/7/1675 |
| _version_ | 1797607507098599424 |
|---|---|
| author | Devendra Joshi Premkumar Chithaluru Divya Anand Fahima Hajjej Kapil Aggarwal Vanessa Yelamos Torres Ernesto Bautista Thompson |
| author_facet | Devendra Joshi Premkumar Chithaluru Divya Anand Fahima Hajjej Kapil Aggarwal Vanessa Yelamos Torres Ernesto Bautista Thompson |
| author_sort | Devendra Joshi |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T05:30:54Z |
| format | Article |
| id | doaj.art-958d70a6dc6049b09215f7d5d8714fd4 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T05:30:54Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-958d70a6dc6049b09215f7d5d8714fd42023-11-17T17:09:05ZengMDPI AGMathematics2227-73902023-03-01117167510.3390/math11071675An Evolutionary Technique for Building Neural Network Models for Predicting Metal PricesDevendra Joshi0Premkumar Chithaluru1Divya Anand2Fahima Hajjej3Kapil Aggarwal4Vanessa Yelamos Torres5Ernesto Bautista Thompson6Department of CSE, Koneru Lakshmaiah Education Foundation, Guntur 522302, Andhra Pradesh, IndiaDepartment of Computer Science and Engineering, Chaitanya Bharathi Institute of Technology, Hyderabad 500075, Telangana, IndiaDepartment of Project Management, Universidad Internacional Iberoamericana, Campeche 24560, MexicoDepartment of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaDepartment of CSE, Koneru Lakshmaiah Education Foundation, Guntur 522302, Andhra Pradesh, IndiaHigher Polytechnic School, Universidad Europea del Atlántico, C/Isabel Torres 21, 39011 Santander, SpainDepartment of Project Management, Universidad Internacional Iberoamericana, Campeche 24560, MexicoIn 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.https://www.mdpi.com/2227-7390/11/7/1675evolutionary algorithmauto-correlationmetal priceneural networkcross-validationentropy |
| spellingShingle | Devendra Joshi Premkumar Chithaluru Divya Anand Fahima Hajjej Kapil Aggarwal Vanessa Yelamos Torres Ernesto Bautista Thompson An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices Mathematics evolutionary algorithm auto-correlation metal price neural network cross-validation entropy |
| title | An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices |
| title_full | An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices |
| title_fullStr | An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices |
| title_full_unstemmed | An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices |
| title_short | An Evolutionary Technique for Building Neural Network Models for Predicting Metal Prices |
| title_sort | evolutionary technique for building neural network models for predicting metal prices |
| topic | evolutionary algorithm auto-correlation metal price neural network cross-validation entropy |
| url | https://www.mdpi.com/2227-7390/11/7/1675 |
| work_keys_str_mv | AT devendrajoshi anevolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT premkumarchithaluru anevolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT divyaanand anevolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT fahimahajjej anevolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT kapilaggarwal anevolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT vanessayelamostorres anevolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT ernestobautistathompson anevolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT devendrajoshi evolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT premkumarchithaluru evolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT divyaanand evolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT fahimahajjej evolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT kapilaggarwal evolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT vanessayelamostorres evolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices AT ernestobautistathompson evolutionarytechniqueforbuildingneuralnetworkmodelsforpredictingmetalprices |