Comparative Analysis of Random Forest and LSTM Models in Predicting Financial Indices: A Case Study of S&P 500 and CSI 300

Yuxuan Qian

2024

Abstract

Stock market prediction has long been a topic of significant interest due to its potential financial rewards and the inherent complexity of financial markets. This study investigates the application of two machine learning models, Random Forest (RF) and Long Short-Term Memory networks (LSTM), in predicting the closing prices of the Standard & Pooler’s 500 Index (S&P 500) and the Shanghai Shenzhen 300 Index (CSI 300) indices using historical data from 09/08/2021 to 08/08/2024 by various indicators, respectively. A sliding window method was used to make predictions based on historical data points. The evaluation metrics including R2, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) were used to assess the models' performance. According to the data, LSTM outperforms RF in CSI 300 prediction while RF performs better in S&P 500 prediction. This study shows the applicability of various models and offers empirical support for optimizing asset price prediction models.

Paper Citation

in Harvard Style

Qian Y. (2024). Comparative Analysis of Random Forest and LSTM Models in Predicting Financial Indices: A Case Study of S&P 500 and CSI 300. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 453-461. DOI: 10.5220/0013268700004568

in Bibtex Style

@conference{ecai24,
author={Yuxuan Qian},
title={Comparative Analysis of Random Forest and LSTM Models in Predicting Financial Indices: A Case Study of S&P 500 and CSI 300},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={453-461},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013268700004568},
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 - Comparative Analysis of Random Forest and LSTM Models in Predicting Financial Indices: A Case Study of S&P 500 and CSI 300
SN - 978-989-758-726-9
AU - Qian Y.
PY - 2024
SP - 453
EP - 461
DO - 10.5220/0013268700004568
PB - SciTePress