Proceedings of the 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022)

<Previous Article In Volume
Next Article In Volume>

Comparison of Stock Price Prediction Based on Different Machine Learning Approaches

Authors
Qianqiao Hu1, Songshan Qin2, Shuai Zhang3, *
1Department of Mathematics and Statistics, Zhongnan University of Economics and Law, Wuhan, Hubei, China
2Adam Smith Business School, University of Glasgow, Glasgow, UK
3Antai College of Economics and Management, Shanghai Jiao Tong University, Shanghai, China
*Corresponding author. Email: zhangshauino.1@sjtu.edu.cn
Corresponding Author
Shuai Zhang
Available Online 20 December 2022.
DOI
10.2991/978-94-6463-030-5_24How to use a DOI?
Keywords
Logistic Regression; Random Forest; LightGBM; Model Comparison; Stock Price Forecast
Abstract

The advantages of machine learning model for fuzzy nonlinear data modeling enable it to be well applied to predict complex nonlinear stock price of low signal-to-noise ratio. Most of the research on stock price prediction with machine learning focuses on the effect evaluation or improvement of a single algorithm, while the comparative research on algorithms has little attention. For investors, the first confusion before predicting stock price trend is to choose the appropriate model instead of optimizing. In this paper, we compare the up-or-down classification performance on a series of prediction windows of LightGBM, Random Forest and Logistic Regression on three stocks to verify the consistency of results. Some technical indicators, e.g., Relative Strength Index (RSI), Simple Moving Averages (SMA) etc. are selected as factors to train our models. Encouragingly, the comparison results show that the prediction performance of the models are significantly different in short and long time window. This finding has some guiding significance for the improvement of long-term and short-term forecasting performance. In addition, some useful suggestions based on the conclusion can be put forward to instruct investors to make better quantitative investment.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022)
Series
Atlantis Highlights in Intelligent Systems
Publication Date
20 December 2022
ISBN
978-94-6463-030-5
ISSN
2589-4919
DOI
10.2991/978-94-6463-030-5_24How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Qianqiao Hu
AU  - Songshan Qin
AU  - Shuai Zhang
PY  - 2022
DA  - 2022/12/20
TI  - Comparison of Stock Price Prediction Based on Different Machine Learning Approaches
BT  - Proceedings of the 2022 International Conference on Bigdata Blockchain and Economy Management (ICBBEM 2022)
PB  - Atlantis Press
SP  - 215
EP  - 231
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-030-5_24
DO  - 10.2991/978-94-6463-030-5_24
ID  - Hu2022
ER  -