Influence of Machine Learning and Smart Warehousing in the Global Logistics Sector: A Systematic Review

Maria Jose Lizarribar Chavez E.; Diana Ortiz Carbajal L.; del Rosario Quichca-Vilchez M. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2026) · DOI: 10.18687/laccei2026.1.1.2193

Resumen

This systematic review examined the influence of machine learning (ML) and smart warehousing (SW) on the global logistics sector through the analysis of literature published between 2022 and 2025, following PRISMA guidelines and the PICOC framework. A total of 40 peer-reviewed articles indexed in EBSCO, PROQUEST, REDALYC, ScienceDirect, Scopus, and Web of Science were analyzed. The findings indicate that ML enhances predictive processes such as demand forecasting and route planning, while SW transforms physical operations through automation and Internet of Things (IoT) integration. The synergy between both technologies leads to substantial improvements in operational efficiency, including cost reductions ranging from 15% to 25% and accuracy levels exceeding 99.5%. However, their implementation faces significant barriers, including high investment requirements, a shortage of specialized talent, and technological integration challenges-particularly for SMEs and in developing regions, especially in Latin America. The study concludes that the strategic adoption of ML and SW is essential for logistics digital transformation and requires approaches that balance technical capabilities with change management and the development of sustainable innovation ecosystems.

Instituciones: Universidad Tecnológica del Perú; Universidad Privada del Norte