An Intelligent Neural Network Framework for Multi-Company Last-Mile Delivery: Joint Time–Cost Optimization with LSTM Forecasting and Reinforcement Learning Routing

Habib Muhammad Jidda; Etemi Joshua Garba; Bawa Mohammed Garba; Habib; Muhammad Jidda; Etemi; Joshua Garba; Bawa; Mohammed Garba

doi:10.56201/ijcsmt.vol.11.no12.2025.pg135.143

An Intelligent Neural Network Framework for Multi-Company Last-Mile Delivery: Joint Time–Cost Optimization with LSTM Forecasting and Reinforcement Learning Routing

Habib Muhammad Jidda, Etemi Joshua Garba, Bawa Mohammed Garba, Habib, Muhammad Jidda, Etemi, Joshua Garba, Bawa, Mohammed Garba

Abstract

In the context of escalating e-commerce demands, last-mile delivery in multi-company logistics environments faces challenges from urban congestion, fragmented operations, and real-time uncertainties, often accounting for over 50% of total supply chain costs. This paper presents a comprehensive neural network framework that integrates Long Short-Term Memory networks for accurate estimated time of arrival forecasting with a reinforcement learning (RL)-based routing engine to achieve joint optimization of delivery time and operational costs across collaborating firms. The modular architecture incorporates a collaboration-aware platform layer that facilitates shared fleet utilization and overlapping zone coordination, processing inputs from logistics databases, real-time traffic APIs, and weather services to enable adaptive decision-making. Theoretical contributions include a Markov Decision Process formulation for multi-agent routing under stochastic constraints, LSTM gating mechanisms enhanced for non-stationary temporal sequences, and a reward function that balances time penalties, fuel costs, and collaboration incentives via weighted multi-objective optimization. Simulations on the Lagos delivery datasets demonstrate 12-15% reductions in joint time-cost metrics compared to baseline heuristics, with robustness to peak-hour volatility. The framework addresses key gaps in existing single-firm, static models by enabling scalable, privacy-preserving multi-stakeholder integration, paving the way for sustainable intelligent transportation systems in dense cities.

Keywords

Last-mile deliverymulti-company logisticsLong Short-Term Memoryroute optimizationMarkov Decision Process.

References

Aktas, E., Bourlakis, M., & Zissis, D. (2020). Collaboration in the last mile: Evidence from grocery deliveries. International Journal of Logistics Research and Applications. Advance online publication. Boysen, N., Fedtke, S., & Schwerdfeger, S. (2021). Last-mile delivery concepts: A survey from an operational research perspective. OR Spectrum, 43(1), 1–58. From, K., & Mangan, K. (2020). Eliminating Last-Mile Inefficiencies in the Trucking Industry. MIT Supply Chain Management Capstone Project. Gao, H., & Lu, Z. (2021). Logistics Route Optimization Based on Improved Particle Swarm Optimization. Applied Soft Computing, 101, 107065. Gevaers, R., Van de Voorde, E., & Vanelslander, T. (2014). Cost Modelling and Simulation of Last mile Characteristics in an Innovative B2C Supply Chain Environment with Implications on Urban Areas and Cities. Procedia - Social and Behavioral Sciences, 125, 398–411. Küp, E. T., Cebeci, S., Bayram, B., Ayd?n, G., Bozkaya, B., & Akhavan-Tabatabaei, R. (2024). An Integrated Framework for Dynamic Vehicle Routing Problems with Pick-up and Delivery Time Windows and Shared Fleet Capacity Planning. Symmetry, 16(4), 505. Liu, Y. (2024). AI and IoT-Based Logistics Distribution Route Optimization Framework. Journal of Transportation Engineering, 150(2), 04022005 Matusiewicz, M., & Ksia? kiewicz, M. (2023). Shared logistics: Enhancing resource utilization and reducing emissions. Logistics and Sustainable Transport, 14(1), 25–40. Mo, Y., Li, X., & Wang, Z. (2023). Predicting drivers' route trajectories in last-mile delivery using a pair-wise attention-based pointer neural network. Transportation Research Part E: Logistics and Transportation Review, 24(3), 2345–2356. Nasiri, M., & Liebchen, B. (2024). Reinforcement learning of optimal active particle navigation. Unpublished manuscript, Institute of Condensed Matter Physics, Technische Universitat Darmstadt, Darmstadt, Germany. Odimarha, A. C., Ayodeji, S. A., & Abaku, E. A. (2024). Machine learning's influence on supply chain and logistics optimization in the oil and gas sector: A comprehensive analysis. Compute Research Journal, 5(3), 725–740. Oloko, O. (2024). Dynamic route optimization in last-mile delivery using predictive analytics: A case study of e-commerce in the U.S. European Journal of Logistics, Purchasing and Supply Chain Management, 12(3), 1–32 Ostermeier, M., Heimfarth, A., & Hübner, A. (2021). Cost-optimal truck-and-robot routing for last- mile delivery. Networks, 78(4), 504–529. Pan, S., Trentesaux, D., Ballot, E., & Huang, G. Q. (2019). Horizontal collaborative transport: Survey of solutions and practical implementation issues. International Journal of Production Research, 57(15–16), 5340–5361. Qu, L., & Li, H. (2022). Analysis of distribution path optimization algorithm based on big data technology. Journal of King Saud University – Science, 34(3), 102019. Savelsbergh, M., & Van Woensel, T. (2016). City logistics: Challenges and opportunities. Transportation Science, 50(2), 579–590. Servos, N., Liu, X., Teucke, M., & Freitag, M. (2020). Travel time prediction in a multimodal freight transport relation using machine learning algorithms. Logistics, 4(1), 1–15. Torres, L., Smith, J., & Patel, R. (2024). Many-objective sectorization for last-mile delivery optimization A decision support system. ScienceDirect. 255(1), 124-559 Wang, Y., Zhang, J., Assogba, K., Liu, Y., Xu, M., & Wang, Y. (2018). Collaboration and transportation resource sharing in multiple centers vehicle routing optimization with delivery and pickup. Knowledge-Based Systems, 161, 258–270.

An Intelligent Neural Network Framework for Multi-Company Last-Mile Delivery: Joint Time–Cost Optimization with LSTM Forecasting and Reinforcement Learning Routing

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY