Hybrid XGBoost and LSTM Model Design Based on Attention Mechanism for Real-Time Stock Needs Prediction
International Journal of Contemporary Sciences (IJCS) · 29.10.2026 · 4 (10) · 2485-2490
DOI: 10.55927/famq9b54 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Contemporary Sciences (IJCS), online erschienen am 29.10.2026. Verfasst von Julia Totong und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Uncertainty in the supply chain and high fluctuations in market demand push companies to have a stock demand forecasting system that is accurate and responsive in real-time. Conventional forecasting models often fail to capture non-linear patterns and long-term temporal relationships in inventory transaction time series data. This study proposes a new hybrid model architecture that combines Extreme Gradient Boosting (XGBoost) for non-linear feature extraction and Long Short-Term Memory (LSTM) reinforced with an Attention Mechanism to selectively capture long-term temporal dependencies. The model evaluation is tested using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) metrics. The experiment results show that the hybrid XGBoost-LSTM-Attention model can outperform single models (pure LSTM or XGBoost alone) with a 14.2% decrease in MAPE, making it very effective to implement for real-time stock management systems
Zitieren
APA
Totong, J., Sanders, A., & Kusumah, N. P. W. (2026). Hybrid XGBoost and LSTM Model Design Based on Attention Mechanism for Real-Time Stock Needs Prediction. International Journal of Contemporary Sciences (IJCS), 4(10), 2485-2490. https://doi.org/10.55927/famq9b54
Vancouver
Totong J, Sanders A, Kusumah NPW. Hybrid XGBoost and LSTM Model Design Based on Attention Mechanism for Real-Time Stock Needs Prediction. International Journal of Contemporary Sciences (IJCS). 2026;4(10):2485-2490. doi:10.55927/famq9b54
BibTeX
@article{Totong2026,
author = {Totong, Julia and Sanders, Albert and Kusumah, Nethanie Paramita Wijaya},
title = {Hybrid XGBoost and LSTM Model Design Based on Attention Mechanism for Real-Time Stock Needs Prediction},
journal = {International Journal of Contemporary Sciences (IJCS)},
year = {2026},
volume = {4},
number = {10},
pages = {2485--2490},
doi = {10.55927/famq9b54}
}
EUVIMED