DOI:
https://doi.org/10.64539/sjcs.v2i1.2026.407Keywords:
Demand forecasting, Medical relief supply chain, Tree-based machine learning, Hyperparameter optimization, CRISP-DMAbstract
Accurate demand forecasting is critical in medical relief supply chains where prediction errors can lead to stockouts, delayed response, or inefficient allocation of limited resources. While machine learning (ML) approaches have demonstrated superior predictive capabilities compared to traditional statistical methods and existing research often treats ML as a homogeneous category and rarely conducts systematic benchmarking within specific algorithm families. Furthermore, many studies rely on default model configurations that limiting the reproducibility and failing to fully assess its robustness under volatile demand conditions common in humanitarian logistics. This study addresses these gaps by systematically evaluating multiple tree-based machine learning algorithms for medical relief supply demand forecasting under a structured framework. The research integrates GridSearchCV as hyperparameter optimization, repeated K-fold cross-validation, and statistical significance testing to ensure fair comparison and robustness assessment. The findings indicate that advanced gradient boosting models outperform single-tree and simpler ensemble approaches in terms of predictive accuracy and stability. CatBoost consistently achieved the lowest prediction errors, the narrowest residual dispersion, and the most stable cross-validation performance. Although statistically comparable to other advanced boosting frameworks, CatBoost demonstrated superior robustness during volatile demand conditions and demand surges. These results provide both methodological and practical contributions by establishing a benchmarking framework and identifying a stable forecasting model that suitable for operational deployment in AI-driven medical relief inventory system.
References
[1] K. Douaioui, R. Oucheikh, O. Benmoussa, and C. Mabrouki, “Machine Learning and Deep Learning Models for Demand Forecasting in Supply Chain Management: A Critical Re-view,” Applied System Innovation, vol. 7, no. 5, 2024. https://doi.org/10.3390/asi7050093.
[2] I. A. Mohammed and J. Mandal, “Forecasting accuracy through machine learning in sup-ply chain management,” International Journal of Supply Chain Management, vol. 9, no. 6, pp. 8–24, 2024. https://doi.org/10.47604/ijscm.3074.
[3] S. Pal, “Advancing Multi-Product Warehousing: The Impact and Nuances of Machine Learning-Based Demand Forecasting,” Journal of Supply Chain Analytics, vol. 7, no. 2, pp. 210–229, 2024.
[4] R. Saha, S. Shofiullah, S. Faysal, and A. Happy, “Systematic Literature Review on Artificial Intelligence Applications In Supply Chain Demand Forecasting,” SSRN Electronic Journal, paper no. 5062817, 2024. https://dx.doi.org/10.2139/ssrn.5062817.
[5] L. Goel, N. Nandal, S. Gupta, M. Karanam, L. P. Yeluri, A. K. Pandey, O. I. Rozhdestven-skiy, and P. Grabovyg, “Revealing the dynamics of demand forecasting in supply chain management: a holistic investigation,” Cogent Engineering, vol. 11, no. 1, Art. no. 2368104, 2024. https://doi.org/10.1080/23311916.2024.2368104.
[6] V. P. Parthasarathy, “Machine Learning Algorithms in Supply Chain Forecasting: Accura-cy, Efficiency, and Scalability Perspectives,” International Journal of Artificial Intelligence, Data Science, and Machine Learning, vol. 4, no. 1, pp. 31–39, 2023. https://doi.org/10.63282/3050-9262.IJAIDSML-V4I1P104.
[7] M. A. Jahin, M. S. H. Shovon, J. Shin, I. A. Ridoy, and M. F. Mridha, “Big data-supply chain management framework for forecasting: Data preprocessing and machine learning tech-niques,” arXiv preprint, arXiv:2307.12971, 2023. https://doi.org/10.48550/arXiv.2307.12971.
[8] S. Birim, I. Kazancoglu, S. K. Mangla, A. Kahraman, and Y. Kazancoglu, “The derived demand for advertising expenses and implications on sustainability: a comparative study using deep learning and traditional machine learning methods,” Annals of Operations Re-search, vol. 339, no. 1, pp. 131–161, 2024. https://doi.org/10.1007/s10479-021-04429-x.
[9] E. M. Onyema, K. K. Almuzaini, F. U. Onu, D. Verma, U. S. Gregory, M. Puttaramaiah, and R. K. Afriyie, “Prospects and challenges of using machine learning for academic forecast-ing,” Computational Intelligence and Neuroscience, vol. 2022, Art. no. 5624475, 2022. https://doi.org/10.1155/2022/5624475.
[10] A. ul Husna, S. H. Amin, and A. Ghasempoor, “Machine learning techniques and multi-objective programming to select the best suppliers and determine the orders,” Machine Learning with Applications, vol. 19, Art. no. 100623, 2025. https://doi.org/10.1016/j.mlwa.2025.100623.
[11] D. Koutsandreas, E. Spiliotis, F. Petropoulos, and V. Assimakopoulos, “On the selection of forecasting accuracy measures,” Journal of the Operational Research Society, vol. 73, no. 5, pp. 937–954, 2022. https://doi.org/10.1080/01605682.2021.1892464.
[12] C. B. Mupparaju, M. Nalluri, A. S. Rongali, and B. Ananthan, “An Efficient Food Distribu-tion and Logistics Based on Supply Chain,” in Proc. 3rd Int. Conf. Artificial Intelligence for Internet of Things (AIIoT), pp. 1–6, IEEE, May 2024. https://doi.org/10.1109/AIIoT58432.2024.10574746.
[13] M. S. Vhatkar, P. S. Mahajan, R. D. Raut, N. Cheikhrouhou, and S. Ghoshal, “Optimized hy-perparameters for retail sales forecasting using grid search,” Engineering Applications of Artificial Intelligence, vol. 158, Art. no. 111472, 2025. https://doi.org/10.1016/j.engappai.2025.111472.
[14] J. Feizabadi, “Machine learning demand forecasting and supply chain performance,” In-ternational Journal of Logistics Research and Applications, vol. 25, no. 2, pp. 119–142, 2022. https://doi.org/10.1080/13675567.2020.1803246.
[15] V. Plotnikova, M. Dumas, and F. P. Milani, “Applying the CRISP-DM data mining process in the financial services industry: Elicitation of adaptation requirements,” Data & Knowledge Engineering, vol. 139, Art. no. 102013, 2022. https://doi.org/10.1016/j.datak.2022.102013.
[16] A. Mansoori, M. Zeinalnezhad, and L. Nazarimanesh, “Optimization of Tree‐Based Ma-chine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm,” Journal of Healthcare Engineering, vol. 2023, Art. no. 9673395, 2023. https://doi.org/10.1155/2023/9673395.
[17] F. Petropoulos et al., “Forecasting: theory and practice,” International Journal of Forecasting, vol. 38, no. 3, pp. 705–871, 2022. https://doi.org/10.1016/j.ijforecast.2021.11.001.
[18] C. Schröer, F. Kruse, and J. M. Gómez, “A systematic literature review on applying CRISP-DM process model,” Procedia Computer Science, vol. 181, pp. 526–534, 2021. https://doi.org/10.1016/j.procs.2021.01.199.
[19] M. A. Mediavilla, F. Dietrich, and D. Palm, “Review and analysis of artificial intelligence methods for demand forecasting in supply chain management,” Procedia CIRP, vol. 107, pp. 1126–1131, 2022. https://doi.org/10.1016/j.procir.2022.05.119.
[20] A. Husna, S. H. Amin, and B. Shah, “Demand forecasting in supply chain management us-ing different deep learning methods,” in Demand Forecasting and Order Planning in Supply Chains and Humanitarian Logistics. Hershey, PA, USA: IGI Global, 2021, pp. 140–170. https://doi.org/10.4018/978-1-7998-3805-0.ch005.
[21] A. Forootani, M. Rastegar, and A. Sami, “Short-term individual residential load forecast-ing using an enhanced machine learning-based approach based on a feature engineering framework: A comparative study with deep learning methods,” Electric Power Systems Research, vol. 210, Art. no. 108119, 2022. https://doi.org/10.1016/j.epsr.2022.108119.
[22] J. C. Cresswell and T. Kim, “Scaling up diffusion and flow-based XGBoost models,” arXiv preprint, arXiv:2408.16046, 2024. https://doi.org/10.48550/arXiv.2408.16046.
[23] Z. Zhang, T. Zhang, and J. Li, “Unbiased gradient boosting decision tree with unbiased fea-ture importance,” arXiv preprint, arXiv:2305.10696, 2023. https://doi.org/10.48550/arXiv.2305.10696.
[24] T. Samal and A. Ghosh, “Ensemble-based predictive analytics for demand forecasting in multi-channel retailing,” Expert Systems with Applications, Art. no. 130212, 2025. https://doi.org/10.1016/j.eswa.2025.130212.
[25] A. Géron, “Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow,” 2nd ed. Sebastopol, CA, USA: O’Reilly Media, 2022. https://books.google.co.id/books?id=X5ySEAAAQBAJ.
[26] M. Mohammadagha, “Hyperparameter Optimization Strategies for Tree-Based Machine Learning Models Prediction: A Comparative Study of AdaBoost, Decision Trees, and Ran-dom Forest,” Decision Trees, and Random Forest, Apr. 11, 2025. https://dx.doi.org/10.2139/ssrn.5226457.
[27] R. G. Goriparthi, “Optimizing Supply Chain Logistics Using AI and Machine Learning Al-gorithms,” International Journal of Advanced Engineering Technologies and Innovations, vol. 1, no. 2, pp. 279–298, 2021.
[28] T. O. Hodson, “Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not,” Geosci. Model Dev., vol. 2022, pp. 1–10, 2022. https://doi.org/10.5194/gmd-15-5481-2022.
[29] D. S. K. Karunasingha, “Root mean square error or mean absolute error? Use their ratio as well,” Inf. Sci., vol. 585, pp. 609–629, 2022. https://doi.org/10.1016/j.ins.2021.11.036.
[30] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis eval-uation,” PeerJ Comput. Sci., vol. 7, p. e623, 2021. https://doi.org/10.7717/peerj-cs.623.
[31] B. Bischl, M. Binder, M. Lang, T. Pielok, J. Richter, S. Coors, J. Thomas, T. Ullmann, M. Becker, A.-L. Boulesteix, and M. Lindauer, “Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 13, no. 2, p. e1484, 2023. https://doi.org/10.1002/widm.1484.
[32] T. Althaqafi, F. Saleem and A. A. M. Al-Ghamdi. “Enhancing student performance predic-tion: the role of class imbalance handling in machine learning models". Discover Compu-ting., vol. 28, no. 1, p. 79, 2025. https://doi.org/10.1007/s10791-025-09576-4.
[33] S. F. Stumpfe and S. C. Shongwe, “Comparative analysis and optimisation of machine learning models for regression and classification on structured tabular datasets,” Mathe-matics, vol. 14, no. 3, p. 473, 2026. https://doi.org/10.3390/math14030473.
