Financial time series data forecasting
Time series data forecasting are methods introduced for improving prediction on time series data. In this report, many basic time series forecasting models had been learned to further understand on how to deal with time series data. There are two research papers are learned in this report. The resul...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
2019
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10356/77557 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Time series data forecasting are methods introduced for improving prediction on time series data. In this report, many basic time series forecasting models had been learned to further understand on how to deal with time series data. There are two research papers are learned in this report. The results that obtain by using the methodology in both research papers are compared and discussed. Both methodologies will be using the same datasets which is the Australian Energy Market Operator (AEMO). The software used in these experiments is Matlab. For the first research paper is Knowledge-Based Systems which mainly using Discrete Wavelet Transform (DWT), Empirical Mode Decomposition (EMD) and Random Vector Functional Link network (RVFL). The second research paper is Applied Soft Computing which mainly using EMB, Intrinsic Mode Functions (IMFs) and Deep Belief Network (DBN). By comparing the results using the same error measurements that obtain through these two methodologies, Knowledge-Based Systems and Applied Soft Computing. In conclusion, Knowledge-Based Systems shows a slightly better performance than Applied Soft Computing. |
|---|