Forecast and Analysis for Samsung Stock Price Based on Machine Learning
Wenjing Tu
2024
Abstract
Predicting stock prices is an important area of research within finance, and selecting suitable machine learning models is essential for enhancing prediction accuracy. This study seeks to assess and compare Logistic Regression (LR), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) regarding their effectiveness in stock price forecasting, particularly emphasizing their advantages and limitations when dealing with imbalanced datasets. By examining historical stock data sourced from Yahoo Finance, this research measures the effectiveness of these three models based on accuracy, precision, and recall. The findings indicate that the LR model achieves the highest overall performance, attaining an accuracy rate of 84%. In comparison, the SVM and XGBoost had lower performance, with accuracy rates of 81% and 70%, respectively. These results provide empirical evidence for model selection in finance, emphasizing the effectiveness of simple models when facing class imbalance. Future research will focus on ensemble techniques and the integration of real-time data to improve forecasting accuracy and adaptability under dynamic market conditions.
DownloadPaper Citation
in Harvard Style
Tu W. (2024). Forecast and Analysis for Samsung Stock Price Based on Machine Learning. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 234-238. DOI: 10.5220/0013213900004568
in Bibtex Style
@conference{ecai24,
author={Wenjing Tu},
title={Forecast and Analysis for Samsung Stock Price Based on Machine Learning},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={234-238},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013213900004568},
isbn={978-989-758-726-9},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Forecast and Analysis for Samsung Stock Price Based on Machine Learning
SN - 978-989-758-726-9
AU - Tu W.
PY - 2024
SP - 234
EP - 238
DO - 10.5220/0013213900004568
PB - SciTePress