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

Jingyuan San ()
Additional contact information
Jingyuan San: South China Normal University, Department of Software Engineering

A chapter in Proceedings of the International Workshop on Navigating the Digital Business Frontier for Sustainable Financial Innovation (ICDEBA 2024), 2025, pp 582-591 from Springer

Abstract: 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.

Keywords: Stock Prediction; Machine Learning; Portfolio Optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advbcp:978-94-6463-652-9_61

Ordering information: This item can be ordered from
http://www.springer.com/9789464636529

DOI: 10.2991/978-94-6463-652-9_61

Access Statistics for this chapter

More chapters in Advances in Economics, Business and Management Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().