Deep neural networks for financial time series forecasting
In today’s technologically advanced world, we see computers greatly replace many tasks due to their low cost, convenience, fast speed and high accuracy. Yet, with all the powerful technologies and instruments, it still remains challenging to predict future data using historical records. This is espe...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/140523 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | In today’s technologically advanced world, we see computers greatly replace many tasks due to their low cost, convenience, fast speed and high accuracy. Yet, with all the powerful technologies and instruments, it still remains challenging to predict future data using historical records. This is especially so for investment purpose.
Machine learning and deep learning knowledge are widely used in predicting financial data. Many models have been established and the accuracies of models have been improved drastically over the years. In this paper, we would discuss and compare our proposed forecasting model with the developed ones. We mainly focus on the ensemble Random Vector Functional Link as a forecasting model together with Support Vector Regression and decomposition filters. This project aims to develop a more accurate forecasting model for financial time series. |
|---|