Optimizing NARX-RNN Performance to Predict Precious Metal Futures market
Precious metals offer lucrative investments appealing to investors globally, leading to a surge in demand for accurate forecasts. Published literature for prediction applications often employs Artificial Neural Networks (ANNs), possessing desirable generalization over nonlinear data and design flexi...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference Paper |
| Language: | English |
| Published: |
IEEE
2022
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/95100 |
| _version_ | 1848765968890724352 |
|---|---|
| author | Stephanie, Rengasamy, Dhanuskodi Juwono, Filbert Hilman Nandong, Jobrun Brennan, Andrew Gopal, L. |
| author_facet | Stephanie, Rengasamy, Dhanuskodi Juwono, Filbert Hilman Nandong, Jobrun Brennan, Andrew Gopal, L. |
| author_sort | Stephanie, |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Precious metals offer lucrative investments appealing to investors globally, leading to a surge in demand for accurate forecasts. Published literature for prediction applications often employs Artificial Neural Networks (ANNs), possessing desirable generalization over nonlinear data and design flexibility. Recurrent Neural Networks (RNNs) are a class of ANNs designed for time series forecasts providing superior approximations. Nonlinear Autoregressive with Exogenous input (NARX) is an RNN model with high memory retention properties, applied in this study to predict ten assets from the precious metal futures market, for three-month predictions (April 2021-June 2021). Network inputs are evaluated through feature selection to filter uncorrelated factors from the network dataset. Accuracy of prediction is enhanced through multi-objective Response Surface Methodology (RSM) optimization, as several variables characterize RNN performance. Three key variables are selected for analysis through RSM, providing optimum configuration to obtain targeted outcome. Simulation results reveal that five assets produce acceptable result, showing an improved fitness through RSM-suggested configurations. Observations indicate intercorrelation between RSM inputs, highlighting its efficiency over conventional methods. Implementing additional RSM inputs to develop more complex models might achieve further reliability. This research provides performance improvement measures for RNNs utilized in financial data projections. |
| first_indexed | 2025-11-14T11:43:41Z |
| format | Conference Paper |
| id | curtin-20.500.11937-95100 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T11:43:41Z |
| publishDate | 2022 |
| publisher | IEEE |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-951002024-06-13T04:51:21Z Optimizing NARX-RNN Performance to Predict Precious Metal Futures market Stephanie, Rengasamy, Dhanuskodi Juwono, Filbert Hilman Nandong, Jobrun Brennan, Andrew Gopal, L. Science & Technology Technology Computer Science, Interdisciplinary Applications Green & Sustainable Science & Technology Computer Science Science & Technology - Other Topics Precious metal NARX RNN Optimization RSM RESPONSE-SURFACE METHODOLOGY ARTIFICIAL NEURAL-NETWORK TIME-SERIES OPTIMIZATION Precious metals offer lucrative investments appealing to investors globally, leading to a surge in demand for accurate forecasts. Published literature for prediction applications often employs Artificial Neural Networks (ANNs), possessing desirable generalization over nonlinear data and design flexibility. Recurrent Neural Networks (RNNs) are a class of ANNs designed for time series forecasts providing superior approximations. Nonlinear Autoregressive with Exogenous input (NARX) is an RNN model with high memory retention properties, applied in this study to predict ten assets from the precious metal futures market, for three-month predictions (April 2021-June 2021). Network inputs are evaluated through feature selection to filter uncorrelated factors from the network dataset. Accuracy of prediction is enhanced through multi-objective Response Surface Methodology (RSM) optimization, as several variables characterize RNN performance. Three key variables are selected for analysis through RSM, providing optimum configuration to obtain targeted outcome. Simulation results reveal that five assets produce acceptable result, showing an improved fitness through RSM-suggested configurations. Observations indicate intercorrelation between RSM inputs, highlighting its efficiency over conventional methods. Implementing additional RSM inputs to develop more complex models might achieve further reliability. This research provides performance improvement measures for RNNs utilized in financial data projections. 2022 Conference Paper http://hdl.handle.net/20.500.11937/95100 10.1109/GECOST55694.2022.10010534 English IEEE restricted |
| spellingShingle | Science & Technology Technology Computer Science, Interdisciplinary Applications Green & Sustainable Science & Technology Computer Science Science & Technology - Other Topics Precious metal NARX RNN Optimization RSM RESPONSE-SURFACE METHODOLOGY ARTIFICIAL NEURAL-NETWORK TIME-SERIES OPTIMIZATION Stephanie, Rengasamy, Dhanuskodi Juwono, Filbert Hilman Nandong, Jobrun Brennan, Andrew Gopal, L. Optimizing NARX-RNN Performance to Predict Precious Metal Futures market |
| title | Optimizing NARX-RNN Performance to Predict Precious Metal Futures market |
| title_full | Optimizing NARX-RNN Performance to Predict Precious Metal Futures market |
| title_fullStr | Optimizing NARX-RNN Performance to Predict Precious Metal Futures market |
| title_full_unstemmed | Optimizing NARX-RNN Performance to Predict Precious Metal Futures market |
| title_short | Optimizing NARX-RNN Performance to Predict Precious Metal Futures market |
| title_sort | optimizing narx-rnn performance to predict precious metal futures market |
| topic | Science & Technology Technology Computer Science, Interdisciplinary Applications Green & Sustainable Science & Technology Computer Science Science & Technology - Other Topics Precious metal NARX RNN Optimization RSM RESPONSE-SURFACE METHODOLOGY ARTIFICIAL NEURAL-NETWORK TIME-SERIES OPTIMIZATION |
| url | http://hdl.handle.net/20.500.11937/95100 |