Application of Artificial Intelligence Algorithms in Last-Mile Route Optimization for E-commerce
DOI:
https://doi.org/10.51923/repae.v11i3.408Keywords:
Last Mile, Artificial Intelligence, E-commerceAbstract
The exponential growth of e-commerce has intensified the logistical challenges of the "last mile," the final stage of delivery, which is characterized by high complexity, significant costs, and a direct impact on customer satisfaction and sustainability. In this context, Artificial Intelligence (AI) emerges as a robust solution for route optimization. This paper aims to evaluate and compare the performance of two bio-inspired metaheuristics: Genetic Algorithms (GA) and Ant Colony Optimization (ACO). A simulation was developed and applied to a set of 100 random delivery points, running both algorithms under equivalent computational conditions and parameters (1000 iterations/generations) to minimize the total distance traveled. The results demonstrated the effectiveness of both methods in optimizing the initial routes. However, the comparative analysis revealed the superiority of ACO, which achieved a *percentage distance reduction of 17.9%, surpassing the **14.9%* obtained by GA. Furthermore, ACO exhibited faster convergence, stabilizing the solution around iteration 200, whereas GA required approximately 300 generations. It is concluded that, for the simulated scenario, the cooperative model of ACO proved to be more robust and efficient in solving the routing problem.
Downloads
References
Use of artificial intelligence in last mile delivery | SHS Web of Conferences. Disponível em: <https://www.shs-conferences.org/articles/shsconf/ref/2021/03/shsconf_glob20_04011/shsconf_glob20_04011.html>. Acesso em: 1 out. 2025.
SILVA, V.; AMARAL, A.; FONTES, T. Sustainable Urban Last-Mile Logistics: A Systematic Literature Review. Sustainability, v. 15, n. 3, p. 2285, 26 jan. 2023. DOI: https://doi.org/10.3390/su15032285
Vista do Uma revisão de escopo assistida por inteligência artificial (IA) sobre usos emergentes de ia na pesquisa qualitativa e suas considerações éticas.Disponível em: <https://editora.sepq.org.br/rpq/article/view/729/467>.
Vista do O papel dos algoritmos de inteligência artificial nas redes sociais. Disponível em: <https://revistaseletronicas.pucrs.br/revistafamecos/article/view/34074/19629>.
DORIGO, Marco; STÜTZLE, Thomas. Ant Colony Optimization. Cambridge: MIT Press, 2004. DOI: https://doi.org/10.7551/mitpress/1290.001.0001
GOLDBERG, David E. Genetic Algorithms in Search, Optimization, and Machine Learning. Reading: Addison-Wesley, 1989.
OLIVEIRA, Carlos A. S. (org.). Handbook of Artificial Intelligence and Data Sciences for Routing Problems. Cham: Springer, 2024 DOI: https://doi.org/10.1007/978-3-031-78262-6
POURMOHAMMADREZA, N.; et al. Last-mile logistics with alternative delivery locations: a systematic literature review. Transportation Research Interdisciplinary Perspectives, v. 27, 2025. Disponível em: https://www.sciencedirect.com/science/article/pii/S2590123025001732. Acesso em: 19 dez. 2025.
KOTLARS, Aleksandrs; SKRIBANS, Valerijs. Efficiency, environment and robotization in first and last mile logistics: a literature review. Transportation Research Interdisciplinary Perspectives, v. 27, 2025. DOI: https://doi.org/10.1016/j.trip.2024.101215
GHANEM, Ghazal; et al. Analysis of logistics measures of CEP service providers for the last-mile delivery in small- and medium-sized cities. European Transport Research Review, 2025. Disponível em: https://elib.dlr.de/212298/1/Ghazal_et_al-2025-European_Transport_Research_Review.pdf. Acesso em: 19 dez. 2025. DOI: https://doi.org/10.1186/s12544-025-00706-z
SLOBODAN, Ghazal; et al. Innovative solutions in last mile delivery: concepts, practices and challenges. European Transport Research Review, 2023. Disponível em: https://www.tandfonline.com/doi/full/10.1080/16258312.2023.2173488. Acesso em: 19 dez. 2025.
PANGARIBUAN, M. A. Literature review on vehicle routing problem: approaches, algorithms and current challenges. Journal La Multiapp, v. 7, n. 3, 2025. Disponível em: https://www.newinera.com/index.php/JournalLaMultiapp/article/view/2382. Acesso em: 19 dez. 2025.
REN, T.; et al. Improved ant colony optimization for the vehicle routing problem with split pickup and split delivery. Cleaner Logistics and Supply Chain, v. 6, 2023. Disponível em: https://www.sciencedirect.com/science/article/abs/pii/S2210650223000020. Acesso em: 19 dez. 2025.
CRIADO, R.; LAPORTE, Gilbert. Metaheuristics for sustainable supply chain management. European Journal of Operational Research, 2019.
BRUNI, Maria Elena; FADDA, Edoardo; FEDOROV, Sergei; PERBOLI, Guido. A machine learning optimization approach for last-mile delivery and third-party logistics. Computers & Operations Research, v. 154, 2023. Disponível em: https://www.sciencedirect.com/science/article/pii/S0305054823001260. Acesso em: 19 dez. 2025. DOI: https://doi.org/10.1016/j.cor.2023.106262
EZMIGNA, I.; ALGHAMDI, A. The impact of AI tools on last-mile delivery in the e-commerce sector. IEEE International Conference on Artificial Intelligence Applications, 2024. DOI: https://doi.org/10.1109/DASA63652.2024.10836527
TIWARI, K. V.; et al. An optimization model for vehicle routing problem in last-mile delivery. Expert Systems with Applications, v. 228, 2023. DOI: https://doi.org/10.1016/j.eswa.2023.119789
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 EMERSON APARECIDO MARTINS, GUILHERME LIMA ANTEBI, RAFAEL ALMEIDA, FRETZ SIEVERS JUNIOR (Autor)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Esta obra está licenciada sob uma licença Creative Commons Atribuição - No comercial - Sin derivaciones 4.0 Internacional
1.O(s) autor(es) autoriza(m) a publicação do artigo na revista;
2.O(s) autor(es) garante(m) que a contribuição é original e inédita e que não está em processo de avaliação em outra(s) revista(s);
3.A revista não se responsabiliza pelas opiniões, ideias e conceitos emitidos nos textos, por serem de inteira responsabilidade de seu(s) autor(es);
4.É reservado aos editores o direito de proceder ajustes textuais e de adequação do artigos às normas da publicação.
1.1 Copyright Statement
This journal is licensed under a Creative Commons Attribution-Non Commercial-No Derivers 4.0 International license.
1. The author (s) authorize the publication of the article in the journal;
2. The author (s) warrant that the contribution is original and unpublished and is not in the process of being evaluated in other journal (s);
3. The journal is not responsible for the opinions, ideas and concepts emitted in the texts, as they are the sole responsibility of its author (s);
4. The editors are entitled to make textual adjustments and to adapt the articles to the standards of publication.
