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

Abstract

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 framewor k. A tota l 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 ph ys ical operations through automation and Internet of Things (IoT) integration. The synergy between both technologies leads to substa ntial 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, an d 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.