VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1870| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Mai Trong Nhan | en_US |
| dc.date.accessioned | 2024-11-15T04:57:43Z | - |
| dc.date.available | 2024-11-15T04:57:43Z | - |
| dc.date.issued | 2024 | - |
| dc.identifier.uri | https://epub.vgu.edu.vn/handle/dlibvgu/1870 | - |
| dc.description.abstract | Research on external economic factors influencing stock prices and the development of appropriate Machine Learning models for stock price prediction are imperative for the benefit of the global market as a whole and Vietnam specifically. Since Machine Learning in Finance is still a relatively new field, there are not many researches about this topic in Vietnam, which limits its practical application. In contrast, there are several articles on the usefulness of Machine Learning models with varied conclusions around the world. Thus, to offer fresh insights into this area, research on the external economic variables influencing Vietnamese stock prices as well as a methodical evaluation of machine learning models using data from Vietnamese businesses are essential at the moment. This thesis utilized the 11-year data (August 1st, 2013 – July 31st, 2024) from four of the largest Vietnamese companies: Vietnam Dairy Product JSC (VNM), Vingroup JSC (VIC), FPT Corporation (FPT), and Vietnam Joint Stock Commercial Bank for Industry and Trade (CTG), along with its Volume and external data from the VN 30, Gold, Crude Oil, Bitcoin, US 30, S&P 500 VIX, NASDAQ, and USD/VND Exchange Rate for correlation comparison, and tested the companies’ data extensively under four Machine Learning models (ARIMA, LSTM, Random Forest, and XGBoost) and three training – testing data division ratio (70:30, 75:25, and 80:20). As a result, most of the Vietnamese companies had heavy dependency on the stock market fluctuations, especially foreign ones like US 30 and NASDAQ, while the 70:30 ratio and LSTM model proved to be the most efficient, with the best recoded test (FPT) having MSE 0.000589, MAE 0.018675, RMSE 0.024284, and R-square value 0.998993 | en_US |
| dc.language.iso | en | en_US |
| dc.rights | Attribution-NonCommercial 4.0 International | * |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc/4.0/ | * |
| dc.subject | Machine learning | en_US |
| dc.subject | Stock market trading | en_US |
| dc.title | Developing and testing a machine learning-based framework for stock market trading – A case study for Vietnam | en_US |
| dc.type | Thesis | en_US |
| item.fulltext | With Fulltext | - |
| item.languageiso639-1 | other | - |
| item.grantfulltext | restricted | - |
| Appears in Collections: | Computer Science (CS) | |
Files in This Item:
| File | Description | Size | Format | Existing users please Login |
|---|---|---|---|---|
| Developing and testing a machine learning-based framework for stock market trading – A case study for Vietnam.pdf | 25.47 MB | Adobe PDF |
Page view(s)
218
checked on Nov 15, 2025
Download(s)
76
checked on Nov 15, 2025
Google ScholarTM
Check
This item is licensed under a Creative Commons License