Random forest-based waste prediction in sustainable graphic production within industry 4.0
DOI:
https://doi.org/10.59476/ilpmt2026.v2i1.790Keywords:
ESG framework, Industry 4.0, key performance indicators, Random Forest, waste predictionAbstract
Graphic production systems generate significant material waste due to de fective prints, registration errors, inefficient material utilization, and subop timal energy management. In printing processes, waste levels can exceed 10%, contributing to environmental burden and increased operational costs. Within Industry 4.0 environments and ESG-oriented production management, companies require measurable, data-driven mechanisms for resource optimization. The aim of this research is to develop and evaluate a Random Forest-based predictive model for production waste forecasting in sustainable graphic systems using key performance indicators as opera tional inputs.
A supervised Random Forest regression model was developed to predict waste levels. Because publicly accessible industrial datasets are unavailable due to confidentiality constraints, simulated KPI data was generated to re flect realistic production variability. Input variables include material waste percentage, machine efficiency, number of defective prints, energy con sumption, and equipment downtime. The synthetic dataset incorporates controlled variability and inter-variable correlations to approximate real production conditions. The data was divided into training and testing sub sets, and cross-validation was applied to ensure model robustness. Model performance was evaluated using mean absolute error, mean squared er ror, and the coefficient of determination.
The Random Forest model achieved an R² value of 0.89, indicating strong explanatory power, with an overall prediction accuracy of 87.32% and a mean absolute error of 3.17%. Simulation scenarios demonstrate substan tial waste reduction potential under AI-supported optimization. In the printing process, waste levels decreased from 12.7% to 5.8%, represent ing a 54.3% reduction. Early detection mechanisms identified 36% of po tential waste events prior to occurrence, enabling proactive intervention. Additional simulation results indicate projected improvements in energy efficiency, defect prevention, and overall cost reduction, estimated at 8%, 12%, and 6%, respectively.
The findings confirm that Random Forest-based predictive modeling can function as an operational tool for ESG-aligned waste management in In dustry 4.0 graphic production. KPI-driven monitoring combined with pre dictive analytics enables early identification of inefficiencies, improved pro duction planning, and systematic reduction of material losses. The model is suitable for integration with sensor systems and production management platforms in smart manufacturing environments, supporting both environ mental sustainability and economic performance.
References
1. Aljamal, D., Salem, A., Khanna, N., & Hegab, H. (2024). Towards sus tainable manufacturing: A comprehensive analysis of circular economy key performance indicators in the manufacturing industry. Sustainable Materials and Technologies, 40, e00953. https://doi.org/10.1016/j.sus mat.2024.e00953
2. Chen, Y., Li, F., Zhou, S., Zhang, X., Zhang, S., Zhang, Q., & Su, Y. (2023). Bayesian optimization based random forest and extreme gradi ent boosting for the pavement density prediction in GPR detection. Con struction and Building Materials, 387, 131564. https://doi.org/10.1016/j. conbuildmat.2023.131564
3. Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of de termination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Sci ence, e623. https://doi.org/10.7717/peerj-cs.623
4. Dwivedi, D., Batra, S., & Pathak, Y. K. (2023). A machine learning based approach to identify key drivers for improving corporate ESG ratings. Journal of Law and Sustainable Development, 11(1), 1–15. https://doi. org/10.37497/sdgs.v11i1.242
5. Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2019). Multi variate data analysis (8th ed.). Cengage Learning.
6. Howard, J., & Gugger, S. (2020). Deep learning for coders with fastai and PyTorch. O’Reilly Media.
7. Hristov, I., & Chirico, A. (2019). The role of sustainability key perfor mance indicators in implementing sustainable strategies. Sustainability, 11, 5742. https://doi.org/10.3390/su11205742
8. Kusiak, A. (2023). Predictive models in digital manufacturing: Research, applications, and future outlook. International Journal of Production Re search, 61(17), 6052–6062. https://doi.org/10.1080/00207543.2022.2122 620
9. Ördek, B., Borgianni, Y., & Coatanea, E. (2024). Machine learning supported manufacturing: A review and directions for future research. Production & Manufacturing Research, 12(1). https://doi.org/10.1080/2 1693277.2024.2326526
10. Rajesh, A. S., Prabhuswamy, M. S., & Krishnasamy, S. (2022). Smart manufacturing through machine learning: A review, perspective, and fu ture directions to the machining industry. Journal of Engineering, 2022, 9735862. https://doi.org/10.1155/2022/9735862
11. Sheppard, C. (2019). Tree-based machine learning algorithms: Decision trees, random forest and boosting (2nd ed.). CreateSpace Independent Publishing Platform.
12. Sun, L., Ji, Y., Zhu, X., & Peng, T. (2022). Process knowledge-based ran dom forest regression for model predictive control on a nonlinear pro duction process with multiple working conditions. Advanced Engineering Informatics, 52, 101561. https://doi.org/10.1016/j.aei.2022.101561
13. Wengang, Z., Chongzhi, W., Haiyi, Z., Yongqin, L., & Lin, W. (2021). Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization. Geoscience Fron tiers, 12, 469–477. https://doi.org/10.1016/j.gsf.2020.03.007
14. Zuher, H. A. (2024). Impact quality indicators onto sustainable manufac turing. Journal of Sustainable Development Innovations, 1(4), 137–141. https://doi.org/10.61552/JSI.2024.04.001
15. Ahmed, I., & Raihan, A. S. (2024). Machine learning techniques for sus tainable industrial process control. In S. K. Paul & S. Kumar (Eds.), Com putational intelligence techniques for sustainable supply chain manage ment (pp. 141–176). Elsevier.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Diana Bratić, Suzana Pasanec Preprotić, Denis Jurečić, Jana Žiljak Gršić
This work is licensed under a Creative Commons Attribution 4.0 International License.
