A Stakeholder-aware Decision Support System for Make-to-Order Production Planning Using Retrieval-Augmented Generative Artificial Intelligence

Document Type : Research Article

Authors

Mozhde Rahjoo

Farzad Haghighi Rad

Amir-Reza Abtahi

Department of Operations Management and Information Technology, Faculty of Management, University of Kharazmi, Tehran, Iran.

10.22067/jstinp.2026.98779.1206

Abstract

Make-to-order (MTO) manufacturing involves production planning decisions under uncertain orders, incomplete operational information, and conflicting stakeholder priorities. To address the need for traceable and defensible cross-functional alignment, this study develops a stakeholder-aware, retrieval-augmented-generation-enabled decision support system (DSS) operationalized through a mixed-methods industrial case study. The system integrates empirical data from 200 orders, 279 downtime events, and 400 quality control, nonconformity, and optical testing records. Rather than relying on probabilistic models for execution calculations, the architecture enforces deterministic release gates to evaluate organisational release readiness prior to optimisation. Retrospective evaluation reveals that the gates classified organisational release status, releasing 170 orders and placing 30 orders on HOLD due strictly to quality control (QC) and optical time-domain reflectometer (OTDR) violations. For the organisationally releasable orders, the engine evaluates two benchmark policies (BASE_FIFO and BASE_EDD) together with three generated scenarios (PROFIT, EFFICIENCY, and CONSENSUS) using the implemented E2 stakeholder-weighted evaluation model. The objective weights were obtained through direct preference elicitation (production efficiency = 0.4688, profit = 0.2997, and value added = 0.2314). The baseline policy (BASE_EDD) benchmark achieved the highest E2 stakeholder-weighted score of 0.5664 and maintained an OTD rate of 90.0% for the evaluated dataset. By restricting the local Large Language Model (Llama-3-8B) strictly to an explainable AI (XAI) interaction layer, the system generates source-grounded justifications without altering deterministic data. The primary academic contribution of this research is the structural separation of organisational release control from multi-objective scenario evaluation, providing a verifiable socio-technical framework for complex make-to-order planning.

Keywords

Make-to-order manufacturing

Systems thinking

Decision support system

Retrieval augmented generation

Generative artificial intelligence

Stakeholder Alignment

---

References

An, Y., Chen, X., Gao, K., Zhang, L., Li, Y. and Zhao, Z., 2023. Integrated optimisation of real-time order acceptance and flexible job-shop rescheduling with multi-level imperfect maintenance constraints. Swarm and Evolutionary Computation, 77, p.101243. https://doi.org/10.1016/j.swevo.2023.101243.

Augustsson, H., Churruca, K. and Braithwaite, J., 2020. Change and improvement 50 years in the making: a scoping review of the use of soft systems methodology in healthcare. BMC Health Services Research, 20(1), p.1063. https://doi.org/10.1186/s12913-020-05929-5.

Bhalla, S., Alfnes, E., Hvolby, H.H. and Oluyisola, O., 2023. Sales and operations planning for delivery date setting in engineer-to-order manufacturing: a research synthesis and framework. International Journal of Production Research, 61(21), pp.7302-7332. https://doi.org/10.1080/00207543.2022.2148010.

Cortiñas-Lorenzo, K., Cai, W. and Doherty, G., 2025. Designing, implementing, and evaluating AI explanations: a scoping review of explainable AI frameworks. ACM Transactions on Computer-Human Interaction, 32(6), pp.1-79. https://doi.org/10.1145/3769678.

Françozo, R., Paucar-Caceres, A. and Belderrain, M.C.N., 2022. Combining value-focused thinking and soft systems methodology: a systemic framework to structure the planning process at a special educational needs school in Brazil. Journal of the Operational Research Society, 73(5), pp.994-1013. https://doi.org/10.1080/01605682.2021.1880298.

Garcia, C.I., DiBattista, M.A., Letelier, T.A., Halloran, H.D. and Camelio, J.A., 2024. Framework for LLM applications in manufacturing. Manufacturing Letters, 41, pp.253-263. https://doi.org/10.1016/j.mfglet.2024.09.030.

Ghobakhloo, M., Fathi, M., Iranmanesh, M., Vilkas, M., Grybauskas, A. and Amran, A., 2024. Generative artificial intelligence in manufacturing: opportunities for actualizing Industry 5.0 sustainability goals. Journal of Manufacturing Technology Management, 35(9), pp.94-121. https://doi.org/10.1108/JMTM-12-2023-0530.

Goto, Y. and Miura, H., 2022. Using the soft systems methodology to link healthcare and long-term care delivery systems: a case study of community policy coordinator activities in Japan. International Journal of Environmental Research and Public Health, 19(14), p.8462. https://doi.org/10.3390/ijerph19148462.

Hörbe, R. and Erol, S., 2024. Artificial intelligence in planning and control tasks: a study of potential use cases and perceived challenges in Austrian make-to-order companies. Procedia CIRP, 130, pp.232-237. https://doi.org/10.1016/j.procir.2024.10.081.

Jackson, I., Ivanov, D., Dolgui, A. and Namdar, J., 2024. Generative artificial intelligence in supply chain and operations management: a capability-based framework for analysis and implementation. International Journal of Production Research, 62(17), pp.6120-6145. https://doi.org/10.1080/00207543.2024.2309309.

Jeon, J., Sim, Y., Lee, H., Han, C., Yun, D., Kim, E., Nagendra, S.L., Jun, M.B.G., Kim, Y., Lee, S.W. and Lee, J., 2025. ChatCNC: conversational machine monitoring via large language model and real-time data retrieval augmented generation. Journal of Manufacturing Systems, 79, pp.504-514. https://doi.org/10.1016/j.jmsy.2025.01.018.

Kapulin, D.V. and Russkikh, P.A., 2020. Analysis and improvement of production planning within small-batch make-to-order production. Journal of Physics: Conference Series, 1515(2), p.022072. https://doi.org/10.1088/1742-6596/1515/2/022072.

Kusiak, A., 2025. Generative artificial intelligence in smart manufacturing. Journal of Intelligent Manufacturing, 36(1), pp.1-3. https://doi.org/10.1007/s10845-024-02480-6.

Leng, J., Zheng, K., Li, R., Chen, C., Wang, B., Liu, Q., Chen, X. and Shen, W., 2026. AIGC-empowered smart manufacturing: prospects and challenges. Robotics and Computer-Integrated Manufacturing, 97, p.103076. https://doi.org/10.1016/j.rcim.2025.103076.

Ma, G., da Silva, E.R. and Møller, C., 2024. Digital twin-based demand-driven production planning and scheduling system: a new conceptual framework. Procedia CIRP, 130, pp.705-710. https://doi.org/10.1016/j.procir.2024.10.152.

Mundt, C. and Lödding, H., 2025. Coping with the uncertainties of make-to-order production: a new approach for determining reliable delivery times with the throughput diagram. Production Planning & Control, 36(8), pp.1110-1136. https://doi.org/10.1080/09537287.2024.2344066.

Nikiforidis, K., Kyrtsoglou, A., Vafeiadis, T., Kotsiopoulos, T., Nizamis, A., Ioannidis, D., Votis, K., Tzovaras, D. and Sarigiannidis, P., 2025. Enhancing transparency and trust in AI-powered manufacturing: a survey of explainable AI (XAI) applications in smart manufacturing in the era of industry 4.0/5.0. ICT Express, 11(1), pp.135-148. https://doi.org/10.1016/j.icte.2024.12.001.

Sit, S.K.H. and Lee, C.K.M., 2023. Design of a digital twin in low-volume, high-mix job allocation and scheduling for achieving mass personalization. Systems, 11(9), p.454. https://doi.org/10.3390/systems11090454.

Tang, P.M., Leong, K.K.H., Shaik, N. and Lau, H.C., 2024. Automated conversion of static to dynamic scheduler via natural language. arXiv preprint arXiv:2405.06697. https://doi.org/10.48550/arXiv.2405.06697.

Wattuhewa, S. and Pheerathan, S., 2025. Reflective applications of soft systems methodology (SSM) across contexts. Systemic Practice and Action Research, 38(4), p.31. https://doi.org/10.1007/s11213-025-09748-9.