Proceedings of the International Workshop on Navigating the Digital Business Frontier for Sustainable Financial Innovation (ICDEBA 2024)

<Previous Article In Volume
Next Article In Volume>

Stock Forecasting and Portfolio Optimization Based on ARIMA-GARCH, Random Forest and Monte Carlo Models

Authors
Jingyuan San1, *
1Department of Software Engineering, South China Normal University, Huizhou, 516000, China
*Corresponding author. Email: 20222034035@m.scnu.edu.cn
Corresponding Author
Jingyuan San
Available Online 24 February 2025.
DOI
10.2991/978-94-6463-652-9_61How to use a DOI?
Keywords
Stock Prediction; Machine Learning; Portfolio Optimization
Abstract

Stock forecasting has long been a popular issue in financial markets. Also comparing the effectiveness of different forecasting models is enormously important. In this paper, the prediction accuracy of the traditional Autoregressive Integrated Moving Average-Generalized Autoregressive Conditional Heteroskedasticity (ARIMA-GARCH) model and the machine learning model (Random Forest) was compared. 15 high-tech stocks were selected and predicted through 2 models. This paper then optimized the stock portfolio based on the prediction results. The collected data was pre-processed to generate the model predictions and then the portfolio was optimized using the Monte Carlo algorithm. The ARIMA model used the AIC criterion to select optimal parameters. Additionally, the GARCH model was utilized in conjunction with ARIMA model in order to eliminate the effect of heteroskedasticity. While in the Random Forest model, the training was done by partitioning the training set and the test dataset. The experimental results indicated that the random forest model in machine learning provided more accurate prediction results than the ARIMA-GARCH model. Additionally, the optimized portfolio showed very substantial expected returns.

Copyright
© 2025 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 International Workshop on Navigating the Digital Business Frontier for Sustainable Financial Innovation (ICDEBA 2024)
Series
Advances in Economics, Business and Management Research
Publication Date
24 February 2025
ISBN
978-94-6463-652-9
ISSN
2352-5428
DOI
10.2991/978-94-6463-652-9_61How to use a DOI?
Copyright
© 2025 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  - Jingyuan San
PY  - 2025
DA  - 2025/02/24
TI  - Stock Forecasting and Portfolio Optimization Based on ARIMA-GARCH, Random Forest and Monte Carlo Models
BT  - Proceedings of the International Workshop on Navigating the Digital Business Frontier for Sustainable Financial Innovation (ICDEBA 2024)
PB  - Atlantis Press
SP  - 582
EP  - 591
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-652-9_61
DO  - 10.2991/978-94-6463-652-9_61
ID  - San2025
ER  -