Multivariate Jute Forecasting Using Ensembled Learning for Supply Chain Optimization
DOI:
https://doi.org/10.38032/scse.2025.3.19Keywords:
Agriculture, Machine Learning, Supply Chain ManagementAbstract
Reliable forecasts of crop production and yield are critical to improving food security and optimizing agricultural supply chains. Through utilizing machine learning (ML) techniques, this study seeks to optimize Bangladesh's jute supply chain through multivariate forecasting. It focuses on evaluating six ensemble learning models in order to forecast jute yield and production. Algorithms including Random Forest (RF), Gradient Boosting (GB), Category Boosting (CatBoost), Adaptive Boosting (AdaBoost), Light Gradient Boosting (LightGBM), and Extreme Gradient Boosting (XGBoost) were employed and their performance was thoroughly assessed to forecast yield rate and production on the basis of historical data. Performance was evaluated utilizing mean squared error (MSE) and R2 scores to determine the best model. With the lowest MSE of 0.0820 and the highest R² of 0.9199, LightGBM was found to be the best-performing model, showcasing its superior accuracy in identifying intricate patterns and complex dependencies in the dataset. The findings demonstrate how LightGBM may lessen inefficiencies and lessen supply chain instability in the jute industry, which has historically been plagued by erratic weather patterns and shifting consumer demand. This study applies ensemble learning techniques specifically to jute forecasting and is one of the first to combine yield rate and production in a single multivariate framework. It is anticipated that the improved predictive capability of the model will help stakeholders such as farmers, traders, and policymakers to enhance decision-making, reduce waste, and promote better resource allocation across the supply chain. Moreover, the study's established ensemble learning framework's scalable nature provides a means of extending its use to other agricultural sectors in Bangladesh. This study also advances data-driven approaches to crop management and supply chain optimization, which boost sustainability and profitability in the jute sector and beyond.
Downloads
Downloads
Downloads
References
[1] Roy, S., & Lutfar, L. B. (2012). Bast fibres: jute. In Handbook of natural fibres (pp. 39-59). Woodhead Publishing.
[2] Hossain, M. M., & Abdulla, F. (2015). Jute production in Bangladesh: a time series analysis. Journal of Mathematics and Statistics, 11(3), 93-98.
[3] Rahman, M., & Khaled, N. (2011). Global market opportunities in export of jute (No. 93). Centre for Policy Dialogue (CPD).
[4] Moazzem, K. G., Rahman, M. T., & Sobhan, A. (2009). Jute manufacturing sector of Bangladesh: challenges, opportunities, and policy options. Dhaka: Centre for Policy Dialogue.
[5] Tariq, M., Khan, M. A., Muhammad, W., & Ahmad, S. (2023). Fiber crops in changing climate. In Global Agricultural Production: Resilience to Climate Change (pp. 267-282). Cham: Springer International Publishing.
[6] Dahikar, S. S., & Rode, S. V. (2014). Agricultural crop yield prediction using artificial neural network approach. International journal of innovative research in electrical, electronics, instrumentation and control engineering, 2(1), 683-686.
[7] Shakoor, M. T., Rahman, K., Rayta, S. N., & Chakrabarty, A. (2017, July). Agricultural production output prediction using supervised machine learning techniques. In 2017 1st international conference on next generation computing applications (NextComp) (pp. 182-187). IEEE.
[8] Condran, S., Bewong, M., Islam, M. Z., Maphosa, L., & Zheng, L. (2022). Machine learning in precision agriculture: a survey on trends, applications and evaluations over two decades. IEEE Access, 10, 73786-73803.
[9] Moon, S., Lee, S., Jeon, W., & Park, K. J. (2023). Learning-Enabled Network-Control Co-Design for Energy-Efficient Industrial Internet of Things. IEEE Transactions on Network and Service Management.
[10] Tripathi, D., & Biswas, S. K. (2024). Design of a precise ensemble expert system for crop yield prediction using machine learning analytics. Journal of Forecasting.
[11] Rane, N., Choudhary, S. P., & Rane, J. (2024). Ensemble deep learning and machine learning: applications, opportunities, challenges, and future directions. Studies in Medical and Health Sciences, 1(2), 18-41.
[12] Nti, I. K., Zaman, A., Nyarko-Boateng, O., Adekoya, A. F., & Keyeremeh, F. (2023). A predictive analytics model for crop suitability and productivity with tree-based ensemble learning. Decision Analytics Journal, 8, 100311.
[13] Mohamed-Iliasse, M., Loubna, B., & Abdelaziz, B. (2020, October). Is machine learning revolutionizing supply chain?. In 2020 5th International Conference on Logistics Operations Management (GOL) (pp. 1-10). IEEE.
[14] Hadeed, S. J., O'rourke, M. K., Burgess, J. L., Harris, R. B., & Canales, R. A. (2020). Imputation methods for addressing missing data in short-term monitoring of air pollutants. Science of the Total Environment, 730, 139140.
[15] Kulkarni, V. Y., Sinha, P. K., & Petare, M. C. (2016). Weighted hybrid decision tree model for random forest classifier. Journal of The Institution of Engineers (India): Series B, 97, 209-217.
[16] Joly, A. (2017). Exploiting random projections and sparsity with random forests and gradient boosting methods--Application to multi-label and multi-output learning, random forest model compression and leveraging input sparsity. arXiv preprint arXiv:1704.08067.
[17] Andreas, Mayr., Harald, Binder., Olaf, Gefeller., Matthias, Schmid. (2014). 1. The evolution of boosting algorithms. From machine learning to statistical modelling. Methods of Information in Medicine, doi: 10.3414/ME13-01-0122
[18] Shi, Y., Li, J., & Li, Z. (2018). Gradient boosting with piece-wise linear regression trees. arXiv preprint arXiv:1802.05640.
[19] Sprangers, O., Schelter, S., & de Rijke, M. (2021, August). Probabilistic gradient boosting machines for large-scale probabilistic regression. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining (pp. 1510-1520).
[20] Just, A. C., Liu, Y., Sorek-Hamer, M., Rush, J., Dorman, M., Chatfield, R., ... & Kloog, I. (2020). Gradient boosting machine learning to improve satellite-derived column water vapor measurement error. Atmospheric measurement techniques, 13(9), 4669-4681.
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Mohammad Morshed, Faiyaz Bin Mahmud, Md Jawad Bin Rouf, Mohammad Mynul Islam Mahin (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All the articles published by this journal are licensed under a Creative Commons Attribution 4.0 International License
