Predictive Analytics Frameworks for Strengthening U.S. Manufacturing Efficiency
International Journal of Scientific Research in Science, Engineering and Technology · 01.10.2025 · 12 (5) · 533-562
DOI: 10.32628/ijsrset25125417 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 01.10.2025. Verfasst von Mohamed Sheriff Jalloh und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Manufacturing efficiency is a critical determinant of industrial competitiveness, particularly in the context of the United States manufacturing sector where operational productivity directly influences economic growth and technological leadership. The emergence of Industry 4.0 technologies has created new opportunities for leveraging predictive analytics to enhance manufacturing performance through data-driven operational decision-making. This study proposes a predictive analytics framework designed to strengthen manufacturing efficiency by integrating machine learning forecasting models with operational manufacturing datasets. The framework utilizes key operational variables such as machine runtime, production throughput, equipment temperature, vibration signals, downtime events, and production demand indicators to model manufacturing performance dynamics. Three predictive modeling techniques Random Forest Regression, Gradient Boosting Machine, and Artificial Neural Networks were implemented to evaluate the effectiveness of predictive analytics in forecasting manufacturing efficiency and operational performance. Model performance was assessed using quantitative evaluation metrics including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and prediction accuracy. The results indicate that predictive analytics significantly improves operational efficiency by increasing machine utilization, reducing equipment downtime, and improving production throughput. Among the models evaluated, Artificial Neural Networks demonstrated the highest predictive accuracy due to their ability to capture complex nonlinear relationships among operational variables. The findings highlight the importance of integrating predictive analytics within smart manufacturing environments to support proactive operational management and predictive maintenance strategies. The proposed framework contributes to Industry 4.0 manufacturing systems by enabling real-time performance monitoring and intelligent production optimization. Practical implications suggest that manufacturing organizations should deploy industrial Internet of Things (IIoT) sensor infrastructures, integrate predictive analytics platforms with manufacturing execution systems, and adopt AI-driven decision-support tools. The study concludes by identifying future research opportunities involving reinforcement learning, edge AI-enabled industrial analytics, and digital twin based predictive production planning systems for next-generation smart manufacturing environments.
Zitieren
APA
Jalloh, M. S., & Bamigwojo, O. V. (2025). Predictive Analytics Frameworks for Strengthening U.S. Manufacturing Efficiency. International Journal of Scientific Research in Science, Engineering and Technology, 12(5), 533-562. https://doi.org/10.32628/ijsrset25125417
Vancouver
Jalloh MS, Bamigwojo OV. Predictive Analytics Frameworks for Strengthening U.S. Manufacturing Efficiency. International Journal of Scientific Research in Science, Engineering and Technology. 2025;12(5):533-562. doi:10.32628/ijsrset25125417
BibTeX
@article{Jalloh2025,
author = {Jalloh, Mohamed Sheriff and Bamigwojo, Otugene Victor},
title = {Predictive Analytics Frameworks for Strengthening U.S. Manufacturing Efficiency},
journal = {International Journal of Scientific Research in Science, Engineering and Technology},
year = {2025},
volume = {12},
number = {5},
pages = {533--562},
doi = {10.32628/ijsrset25125417}
}
EUVIMED