Please use this identifier to cite or link to this item:
https://hdl.handle.net/10216/134180| Author(s): | Nuno Miguel de Barbosa Ferreira |
| Title: | Time series vs regression, which is the best approach? |
| Issue Date: | 2021-03-29 |
| Description: | In management and administrative situations the need for planning is great and very valuable. Forecasting is a tool that aims to provide aid in decision making processes and efficient planning, whether that means learning from past mistakes, decreasing costs, better resource management amongst many other uses. When the data that's being analyzed is ordered over time then it's considered a time-series and its forecasting will try to estimate how that sequence of observations will behave in the future. Since time-series have specific traits it's interesting to convert time-series problems to regression ones. This thesis aims to automatically convert a time-series framework to a state-of-the-art regression framework and compare the two, trying to understand the advantages and disadvantages of the two approaches. |
| Subject: | Engenharia electrotécnica, electrónica e informática Electrical engineering, Electronic engineering, Information engineering |
| Scientific areas: | Ciências da engenharia e tecnologias::Engenharia electrotécnica, electrónica e informática Engineering and technology::Electrical engineering, Electronic engineering, Information engineering |
| DOI: | 10.34626/5hfx-tc95 |
| TID identifier: | 202824160 |
| URI: | https://hdl.handle.net/10216/134180 |
| Document Type: | Dissertação |
| Rights: | restrictedAccess |
| Appears in Collections: | FEUP - Dissertação |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 474760.pdf Restricted Access | Time Series vs Regression, which is the best approach? | 7.64 MB | Adobe PDF | View/Open |
| 474760.1.pdf | Time Series vs Regression, which is the best approach? | 7.64 MB | Adobe PDF | ![]() View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
