Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application
The thesis aims to predict precious metal market prices using a deep learning model known as Nonlinear AutoRegressive with eXogenous input. Market forecasts of the 58 assets selected are evaluated through portfolio techniques such as Mean-Variance and Conditional Value-at-Risk to demonstrate the rea...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2024
|
| Online Access: | http://hdl.handle.net/20.500.11937/96183 |
| _version_ | 1848766109776347136 |
|---|---|
| author | Tjendra, Stephanie Aliana |
| author_facet | Tjendra, Stephanie Aliana |
| author_sort | Tjendra, Stephanie Aliana |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | The thesis aims to predict precious metal market prices using a deep learning model known as Nonlinear AutoRegressive with eXogenous input. Market forecasts of the 58 assets selected are evaluated through portfolio techniques such as Mean-Variance and Conditional Value-at-Risk to demonstrate the real-world application. This investigation provides a framework for future value projection, including the preprocessing stage, feature selection, and dataset construction. Additionally, a novel error measure is proposed to comprehensively assess the estimation accuracy. |
| first_indexed | 2025-11-14T11:45:55Z |
| format | Thesis |
| id | curtin-20.500.11937-96183 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T11:45:55Z |
| publishDate | 2024 |
| publisher | Curtin University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-961832025-05-27T06:45:56Z Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application Tjendra, Stephanie Aliana The thesis aims to predict precious metal market prices using a deep learning model known as Nonlinear AutoRegressive with eXogenous input. Market forecasts of the 58 assets selected are evaluated through portfolio techniques such as Mean-Variance and Conditional Value-at-Risk to demonstrate the real-world application. This investigation provides a framework for future value projection, including the preprocessing stage, feature selection, and dataset construction. Additionally, a novel error measure is proposed to comprehensively assess the estimation accuracy. 2024 Thesis http://hdl.handle.net/20.500.11937/96183 Curtin University restricted |
| spellingShingle | Tjendra, Stephanie Aliana Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application |
| title | Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application |
| title_full | Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application |
| title_fullStr | Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application |
| title_full_unstemmed | Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application |
| title_short | Predicting Precious Metal Markets using Custom Deep-Learning NARX Network: A Portfolio Application |
| title_sort | predicting precious metal markets using custom deep-learning narx network: a portfolio application |
| url | http://hdl.handle.net/20.500.11937/96183 |