A Risk-Integrated Multi-Objective Optimization Framework for Dynamic Contractor Allocation in Zimbabwe's Commercial Timber Value Chain

Zimbabwe's commercial sector in forestry is currently using small and medium scale contractors whereas as much as 70% of harvesting and milling is outsourced, resulting in chronic supply chain inefficiencies that previous Enterprise Resource Planning (ERP) systems cannot address. In this paper, we present a Dynamic Resource Allocation Framework (DRAF) for bridging the decision-intelligence gap by feeding the XGBoost-derived contractor risk probabilities directly into a Non-dominated Sorting Genetic Algorithm II (NSGA-II) multi-objective optimizer to allow estate managers to obtain the Pareto-optimal contractor-block-mill assignment that simultaneously minimizes cost, maximizes expected timber recovery, minimizes expected delay, maximizes operational reliability, and minimizes transport distance. The proposed framework was developed and evaluated on an 828,789-record Virtual ERP dataset built on the USDA Forest Service Timber Harvests Feature Layer and calibrated to Manicaland's forestry areas; no proprietary Zimbabwean ERP records were available, so the results are interpreted as synthetic benchmark evidence rather than production validation. XGBoost performed better than (ROC-AUC 0.600) Logistic Regression baseline on the holdout ROC-AUC of 0.965, recall of 0.999, and F1 of 0.867. The NSGA-II optimizer gave 64 fully feasible Pareto solutions for the balanced and high-recovery cases and identified a constraint-feasibility threshold for the strict, low-risk scenario, articulating a suitable operational trade-off. An interactive Dash decision-support prototype was functionally demonstrated across all evaluated pipeline components and used to present the framework's outputs to non-technical estate managers. A structured post-demonstration stakeholder evaluation with 30 practitioners produced a mean formative satisfaction score of 4.19/5.0. Field usability testing, real-data validation, and a formal ablation of the ML-risk integration remain necessary future validation steps. As an extension to the research, this research is also known as the first integrated, domain-specific decision-intelligence framework for forestry contractor allocation in Sub-Saharan Africa in this context and provides a replicable model for best practice, methodological framework for risk-integrated multi-objective optimization in resource and other intensive industries.

XGBoost; NSGA-II; multi-objective optimization; contractor risk; forestry supply chain

1. Timber Producers Federation, Annual Timber Sector Performance Report 2024. Harare: TPF Zimbabwe, 2024. [Google Scholar] [Crossref]

2. African Forest Forum, Forestry Value Chain Analysis in Selected African Countries. Nairobi: AFF, 2023. [Google Scholar] [Crossref]

3. "Timber production rebounds amid contractor restructuring," Sunday News, Mar. 2, 2025. [Google Scholar] [Crossref]

4. C. S. Tang, "Perspectives in supply chain risk management," Int. J. Prod. Econ., vol. 103, no. 2, pp. 451–488, 2006. [Google Scholar] [Crossref]

5. S. Chibaro, B. Mapani, and T. Dube, "Predictive analytics in Zimbabwean forestry operations," African J. Forestry Res., vol. 12, no. 2, pp. 88–104, 2024. [Google Scholar] [Crossref]

6. Chips Business Solutions, ERP Implementation in Zimbabwe's Timber Industry. Harare: CBS, 2024. [Google Scholar] [Crossref]

7. L. Zhao, X. Li, and Y. Sun, "Machine learning–based contractor risk assessment in industrial supply chains," Expert Syst. Appl., vol. 235, p. 121247, 2024. [Google Scholar] [Crossref]

8. O. Filani, P. Ndlovu, and K. Moyo, "Risk scoring frameworks in emerging market supply chains," Int. J. Supply Chain Anal., vol. 4, no. 1, pp. 22–39, 2025. [Google Scholar] [Crossref]

9. L. Grinsztajn, E. Oyallon, and G. Varoquaux, "Why do tree-based models still outperform deep learning on tabular data?" in Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 35, pp. 507–520, 2022. [Google Scholar] [Crossref]

10. K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, "A fast and elitist multiobjective genetic algorithm: NSGA-II," IEEE Trans. Evol. Comput., vol. 6, no. 2, pp. 182–197, Apr. 2002. [Google Scholar] [Crossref]

11. K. T. Malladi and T. Sowlati, "Optimization in forest supply chain management: A review," Curr. Forestry Rep., vol. 7, no. 2, pp. 100–118, 2021. [Google Scholar] [Crossref]

12. J. Rix, B. Wolff, and F. Müller, "Machine learning applications in forestry harvesting operations: A systematic review," Eur. J. For. Res., vol. 142, no. 4, pp. 771–790, 2023. [Google Scholar] [Crossref]

13. D. Ivanov and A. Dolgui, "Viability of intertwined supply networks: Extending the supply chain resilience angles," Int. J. Prod. Res., vol. 58, no. 10, pp. 2904–2915, 2020. [Google Scholar] [Crossref]

14. R. Hevner, S. T. March, J. Park, and S. Ram, "Design science in information systems research," MIS Q., vol. 28, no. 1, pp. 75–105, Mar. 2004. [Google Scholar] [Crossref]

15. K. Peffers, T. Tuunanen, M. A. Rothenberger, and S. Chatterjee, "A design science research methodology for information systems research," J. Manage. Inf. Syst., vol. 24, no. 3, pp. 45–77, 2007. [Google Scholar] [Crossref]

16. L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001. [Google Scholar] [Crossref]

17. T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., San Francisco, CA, 2016, pp. 785–794. [Google Scholar] [Crossref]

18. M. Al Mnaseer, M. Alshurideh, and S. Al-Hawary, "Hybrid machine learning approaches for contractor performance classification," J. Bus. Anal., vol. 8, no. 1, pp. 45–63, 2025. [Google Scholar] [Crossref]

19. R. Shwartz-Ziv and A. Armon, "Tabular data: Deep learning is not all you need," Inf. Fusion, vol. 81, pp. 84–90, 2022. [Google Scholar] [Crossref]

20. SGS, Forest Management Certification Report: Zimbabwe Operations. SGS, 2021. [Google Scholar] [Crossref]

21. P. Auger, L. T. Bui, and M. H. Nguyen, "Advances in multi-objective evolutionary algorithms for supply chain optimization," Comput. Oper. Res., vol. 150, p. 106082, 2023. [Google Scholar] [Crossref]

22. M. T. M. Emmerich and A. H. Deutz, "A tutorial on multiobjective optimization: Fundamentals and evolutionary methods," Nat. Comput., vol. 17, no. 3, pp. 585–609, 2018. [Google Scholar] [Crossref]

23. M. Acuna, J. Skinnell, T. Evanson, and R. Mitchell, "Harvesting productivity and cost analysis in forestry operations," Int. J. Forest Eng., vol. 32, no. 3, pp. 202–215, 2021. [Google Scholar] [Crossref]

24. X. Liu, Q. Chen, and F. Wang, "Multi-objective construction scheduling under resource constraints," Autom. Constr., vol. 145, p. 104617, 2023. [Google Scholar] [Crossref]

25. C. Kogler and P. Rauch, "Decision support systems in the forest supply chain: A review of challenges and recent advances," Forests, vol. 13, no. 1, p. 89, 2022. [Google Scholar] [Crossref]

26. C. W. Holsapple, A. Lee-Post, and R. Pakath, "A unified foundation for decision support systems," Decis. Support Syst., vol. 64, pp. 1–10, 2014. [Google Scholar] [Crossref]

27. T. Maxime, G. Kambanje, and B. Nyoni, "Supply chain optimization in Southern African forestry sectors," J. African Ind. Syst., vol. 9, no. 3, pp. 101–119, 2023. [Google Scholar] [Crossref]

28. M. Haddara and A. Elragal, "The readiness of ERP systems for the factory of the future," Procedia Comput. Sci., vol. 64, pp. 721–728, 2015. [Google Scholar] [Crossref]

29. Zimbabwe National Statistics Agency (ZimStat), Zimbabwe Agricultural Statistics Report 2024. Harare: ZIMSTAT, 2024. [Google Scholar] [Crossref]

30. T. Fawcett, "An introduction to ROC analysis," Pattern Recognit. Lett., vol. 27, no. 8, pp. 861–874, Jun. 2006. [Google Scholar] [Crossref]

31. S. Hosseini et al., "Resilient supplier selection and optimal order allocation under disruption risks," Int. J. Prod. Econ., vol. 213, pp. 124–137, 2022. [Google Scholar] [Crossref]

32. Raj et al., "Barriers to the adoption of Industry 4.0 technologies in the manufacturing sector," Int. J. Prod. Econ., vol. 241, p. 108308, 2022. [Google Scholar] [Crossref]

33. A.-L. Boulesteix, S. Lauer, and M. J. Eugster, "A plea for neutral comparison studies in computational sciences," PLOS ONE, vol. 8, no. 4, p. e61562, 2013. (see also: A.-L. Boulesteix et al., "The replication crisis: A statistical point of view," Significance, vol. 17, pp. 8–10, 2020.) [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study