Proceedings of the International Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)

<Previous Article In Volume
Next Article In Volume>

Predictive Analytics for Stock Market Trends Using Ensemble Machine Learning Models

Authors
A. F. M. Rafid Hassan Akand1, Mohammad Shahidullah2, Adib Hossain3, Md Azharul Islam4, Ali Hassan2, Arafat Islam3, Jannatul Ferdousmou2, Md Abdur Rob4, Rakibul Hasan1, *
1College of Business, Westcliff University, Irvine, CA, 92614, USA
2Department of Business Administration, International American University, Los Angeles, CA, 90010, USA
3College of Graduate and Professional Studies, Trine University, Angola, IN, 46703, USA
4Department of Economics, Ohio University, Athens, OH, 45701, USA
*Corresponding author.
Corresponding Author
Rakibul Hasan
Available Online 6 April 2026.
DOI
10.2991/978-94-6239-624-1_9How to use a DOI?
Keywords
S&P 500; Stock Market; Machine Learning; Market Volatility; Ensemble Model
Abstract

We test whether ensemble machine-learning models can pro-duce economically meaningful forecasts for daily S&P 500 returns over January 2000–May 2024 (6,266 trading days; CRSP). Eight technical predictors are engineered to capture momentum and volatility structure. A Random Forest (200 trees) and Gradient Boosting regressor (400 stages) are trained on 2000–2019 and combined in a convex ensemble (60% RF, 40% GB). On the 2020–2024 hold-out sample, the ensemble improves MAE by 3% versus its constituents but fails to beat a naïve zero-return benchmark in out-of-sample R2. A long-only rule that takes positions only when forecasts are positive reduces drawdown and annualised volatility yet delivers only 2.1% CAGR, suggesting limited net value after trading costs. Importance analysis shows MACD and 21-day volatility contribute 39% of the predictive signal, and year-by-year errors confirm strong regime dependence, especially during the COVID-19 crash and the 2022 inflation sell-off. We conclude that tree ensembles aid risk control, but consistent performance likely requires regime-aware or deep sequence approaches with macro-sentiment features.

Copyright
© 2026 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 Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)
Series
Advances in Economics, Business and Management Research
Publication Date
6 April 2026
ISBN
978-94-6239-624-1
ISSN
2352-5428
DOI
10.2991/978-94-6239-624-1_9How to use a DOI?
Copyright
© 2026 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  - A. F. M. Rafid Hassan Akand
AU  - Mohammad Shahidullah
AU  - Adib Hossain
AU  - Md Azharul Islam
AU  - Ali Hassan
AU  - Arafat Islam
AU  - Jannatul Ferdousmou
AU  - Md Abdur Rob
AU  - Rakibul Hasan
PY  - 2026
DA  - 2026/04/06
TI  - Predictive Analytics for Stock Market Trends Using Ensemble Machine Learning Models
BT  - Proceedings of the International Conference on Sustainable Economics and Finance in the Digital Business Transformation (INCOSEF 2025)
PB  - Atlantis Press
SP  - 118
EP  - 128
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-624-1_9
DO  - 10.2991/978-94-6239-624-1_9
ID  - Akand2026
ER  -