A refined methodological approach: Long-term stock market forecasting with XGBoost

One critical research gap that this study fills is artificial intelligence (AI) and machine learning applications that predict equity market index total returns using long-term prediction horizons, and by experimenting with Extreme Gradient Boosting (XGBoost). The presented models achieved significa...

Full description

Saved in:
Bibliographic Details
Main Authors: Sürek Rojen Erik, Lau Wee-Yeap
Format: Article
Language:English
Published: De Gruyter 2025-07-01
Series:Journal of Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1515/jisys-2025-0027
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849242954429890560
author Sürek Rojen Erik
Lau Wee-Yeap
author_facet Sürek Rojen Erik
Lau Wee-Yeap
author_sort Sürek Rojen Erik
collection DOAJ
description One critical research gap that this study fills is artificial intelligence (AI) and machine learning applications that predict equity market index total returns using long-term prediction horizons, and by experimenting with Extreme Gradient Boosting (XGBoost). The presented models achieved significantly higher accuracy rates than the majority class rate, and they obtained better predictive scores in all metrics than the logistic regression model. The best-performing model had a 100% accuracy rate when negative returns were predicted with a p-value of 0.05121. The evidence from this study suggests that XGBoost, a neglected algorithm in the literature, can enable more empirically informed long-term portfolio management decisions regarding overall equity exposure. Moreover, a literature contribution of this study is a refined methodological approach for prospective studies when implementing binary classifiers of prospective stock market returns for enhanced real-life economic utility for investors. The constructed models generated probabilities of whether the S&P 500 will have positive or negative total returns, including dividend payouts, in the subsequent 12 months. The predictive metrics of these models were evaluated against traditional logit models and whether the accuracy rates statistically significantly exceeded the majority class rate.
format Article
id doaj-art-c29fb468aaf8480ca183fc27a9607ee3
institution Kabale University
issn 2191-026X
language English
publishDate 2025-07-01
publisher De Gruyter
record_format Article
series Journal of Intelligent Systems
spelling doaj-art-c29fb468aaf8480ca183fc27a9607ee32025-08-20T03:59:39ZengDe GruyterJournal of Intelligent Systems2191-026X2025-07-013418234610.1515/jisys-2025-0027A refined methodological approach: Long-term stock market forecasting with XGBoostSürek Rojen Erik0Lau Wee-Yeap1Faculty of Business and Economics, Universiti Malaya, 50603 Kuala Lumpur, MalaysiaFaculty of Business and Economics, Universiti Malaya, 50603 Kuala Lumpur, MalaysiaOne critical research gap that this study fills is artificial intelligence (AI) and machine learning applications that predict equity market index total returns using long-term prediction horizons, and by experimenting with Extreme Gradient Boosting (XGBoost). The presented models achieved significantly higher accuracy rates than the majority class rate, and they obtained better predictive scores in all metrics than the logistic regression model. The best-performing model had a 100% accuracy rate when negative returns were predicted with a p-value of 0.05121. The evidence from this study suggests that XGBoost, a neglected algorithm in the literature, can enable more empirically informed long-term portfolio management decisions regarding overall equity exposure. Moreover, a literature contribution of this study is a refined methodological approach for prospective studies when implementing binary classifiers of prospective stock market returns for enhanced real-life economic utility for investors. The constructed models generated probabilities of whether the S&P 500 will have positive or negative total returns, including dividend payouts, in the subsequent 12 months. The predictive metrics of these models were evaluated against traditional logit models and whether the accuracy rates statistically significantly exceeded the majority class rate.https://doi.org/10.1515/jisys-2025-0027computational financequantitative financeai and machine learningstock market returnpredictive modelg17c53c49
spellingShingle Sürek Rojen Erik
Lau Wee-Yeap
A refined methodological approach: Long-term stock market forecasting with XGBoost
Journal of Intelligent Systems
computational finance
quantitative finance
ai and machine learning
stock market return
predictive model
g17
c53
c49
title A refined methodological approach: Long-term stock market forecasting with XGBoost
title_full A refined methodological approach: Long-term stock market forecasting with XGBoost
title_fullStr A refined methodological approach: Long-term stock market forecasting with XGBoost
title_full_unstemmed A refined methodological approach: Long-term stock market forecasting with XGBoost
title_short A refined methodological approach: Long-term stock market forecasting with XGBoost
title_sort refined methodological approach long term stock market forecasting with xgboost
topic computational finance
quantitative finance
ai and machine learning
stock market return
predictive model
g17
c53
c49
url https://doi.org/10.1515/jisys-2025-0027
work_keys_str_mv AT surekrojenerik arefinedmethodologicalapproachlongtermstockmarketforecastingwithxgboost
AT lauweeyeap arefinedmethodologicalapproachlongtermstockmarketforecastingwithxgboost
AT surekrojenerik refinedmethodologicalapproachlongtermstockmarketforecastingwithxgboost
AT lauweeyeap refinedmethodologicalapproachlongtermstockmarketforecastingwithxgboost