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...

Full description

Bibliographic Details
Main Authors: Stephanie, Rengasamy, Dhanuskodi, Juwono, Filbert Hilman, Nandong, Jobrun, Brennan, Andrew, Gopal, L.
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