Comparing the Performance of Four Regression Models in Predicting Stock Returns

DOI

10.2991/978-94-6463-546-1_4How to use a DOI?

Keywords

Stock Returns Prediction; LGBM; Decision Tree; XGBoost; CatBoost

Abstract

In recent years, stock market investment has seen rapid growth, yet many investors may lack sufficient relevant knowledge. This article aims to help investors achieve higher returns by comparing the predictive results of several models. Using four regression models in ML algorithms, namely LightGBM, decision tree, XGBoost, and CatBoost, to predict the returns of 1500 Japanese stocks. By analyzing the RMSE and MAE, the errors are evaluated to assess the accuracy of the models. LightGBM and XGBoost are gradient boosting-based models offering high training speed and accuracy, suitable for large datasets. Decision trees are easy to interpret but prone to overfitting. CatBoost handles categorical variables seamlessly. Comparing RMSE and MAE, all models perform similarly, with XGBoost showing superior performance. This research contributes to stock market prediction by analyzing model strengths and weaknesses, offering insights for future research.

Copyright

© 2024 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)

TY  - CONF
AU  - Zimu Tang
PY  - 2024
DA  - 2024/10/27
TI  - Comparing the Performance of Four Regression Models in Predicting Stock Returns
BT  - Proceedings of the 2024 2nd International Conference on Finance, Trade and Business Management (FTBM 2024)
PB  - Atlantis Press
SP  - 20
EP  - 27
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-546-1_4
DO  - 10.2991/978-94-6463-546-1_4
ID  - Tang2024
ER  -