Hybrid Metaheuristic Inventory Optimization for Short Life-Cycle Products
Sara MESKINE, Hayat EL ASRI
Abstract. Short life-cycle products pose challenges for their high risks of obsolescence and waste and managing them became essential to profitability and sustainability. Conventional inventory models, Economic Order Quantity (EOQ), often redeem unsuitable for volatile demand environments and lead to overstocking or stockouts, which result in increased waste and excess emissions from inefficient demand and transportation planning. This study develops a hybrid optimization algorithm cable of modeling demand to optimize inventory operations under stochastic demand. The model integrates a Discrete-Time Markov Chain Monte Carlo Simulation (DTMC-MCS) under a Genetic Algorithm (GA). To minimize total expected costs from transportation and ordering, the GA adapts dynamically to reorder points; the model fundamentally assigns stockout and obsolescence penalties if necessary to handle the stochasticity of product P0003’s demand, while inherently reducing material waste and carbon footprint. The DTMC captures demand transitions through historical sales, the MCS evaluates each candidate solution, and the GA evolves reorder policies until it achieves maximum cost convergence or generations is reached. The model resulted in an 87% reduction in inventory levels compared to EOQ model. This framework informs practical insights for managing Short Life-Cycle Products under stochastic demand while preserving environmental performance and enhancing economic resilience.
Keywords
Genetic Algorithms, Stochastic Demand, Sustainable Planning, Short Life-Cycle Products, Circular Economy
Published online 4/25/2026, 8 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Sara MESKINE, Hayat EL ASRI, Hybrid Metaheuristic Inventory Optimization for Short Life-Cycle Products, Materials Research Proceedings, Vol. 64, pp 1197-1204, 2026
DOI: https://doi.org/10.21741/9781644904091-147
The article was published as article 147 of the book Energy Futures
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] V. Ikpe and M. Shamsuddoha, Functional Model of Supply Chain Waste Reduction and Control Strategies for Retailers, Sustainable Logistics in the New Era 8 (2024) 17. https://doi.org/10.3390/logistics8010022
[2] United Nations, 2030 Agenda for Sustainable Development, 2015.
[3] S. Agrawala and R. Kr Singh, Analyzing disposition decisions for sustainable reverse logistics: Triple Bottom Line approach, Resour. Conserv. Recycl.150 (2019) 10448. https://doi.org/10.1016/j.resconrec.2019.104448
[4] M. J. Basallo-Triana, et al., Analogue-based demand forecasting of short life-cycle products, Int. J. Prod. Res. 55 (2016) 1-15. https://doi.org/10.1080/00207543.2016.1241443
[5] I. Srikanth and M. Arockiasamy, Deterioration models for prediction of remaining useful lifetime of timber and concrete bridges: A review, J. Traffic and Transp. Eng. 7 (2020) 152-173. https://doi.org/10.1016/j.jtte.2019.09.005
[6] N. Duy Tan, H.S. Kim, L.N.B. Long, D.A. Nguyen, S.S. You, Optimization and inventory management under stochastic demand using metaheuristic algorithm, PLoS ONE, 19 (2024). https://doi.org/10.1371/journal.pone.0286433
[7] C. Cuartas and J. Aguilar, Hybrid algorithm based on reinforcement learning for smart inventory management, J. Intell. Manuf. 34 (2022) 123-149. https://doi.org/10.1007/s10845-022-01982-5
[8] C.Y. Lee, C.Y. Ho, Y.H. Hung, Y.W. Deng, Multi-objective genetic algorithm embedded with reinforcement learning for petrochemical melt-flow-index production scheduling, Appl. Soft Comput. 159 (2024) 111630. https://doi.org/10.1016/j.asoc.2024.111630
[9] Y. Nomura, Z. Liu, T. Nishi, Deep Reinforcement Learning for Dynamic Pricing and Ordering Policies in Perishable Inventory Management, Comput. and Artif. Intell. 15 (2025). https://doi.org/10.3390/app15052421
[10] P. Radhakrishnan, et al., Genetic Algorithm Based Inventory Optimization Analysis in Supply Chain Management, in: Proc. IEEE Int. Adv. Comput. Conf., 2009. https://doi.org/10.1109/IADCC.2009.4809047
[11] R. Accorsi, A. Gallo, R. Manzini, A climate driven decision-support model for the distribution of perishable products, J Clean. Prod., vol. 165 (2017) 917-929. https://doi.org/10.1016/j.jclepro.2017.07.170
[12] M. Geissdoerfer, P. Savaget, N. M.P. Bocken and E. J. Hultink, The Circular Economy – A new sustainability paradigm?, J. Clean. Prod. 143 (2017) 757-768. https://doi.org/10.1016/j.jclepro.2016.12.048
[13] J. Cha, S.M Han, L. Pham, Smart Contract Adoption under Discrete Overdispersed Demand: A Negative Binomial Optimization Perspective, arXiv (2025).
[14] Stevenson, Operations Management. 9th edition. New York, McGraw-Hill, 903 (2007) p. 6.
