Exploring the Influence o Machine Learning in e-Commerce: A Systematic and Bibliometric Review

Abstract

The use of Machine Learning (ML) in e-commerce has revolutionized key processes such as service personalization, dynamic pricing optimization, and sales forecasting, generating a direct impact on both operational efficiency and user experience quality. The objective of this paper is to rigorously identify, analyze, and synthesize the findings of the most relevant studies related to the application of Machine Learning and its impact within the field of e-Commerce. A systematic review was conducted on 66 papers extracted from recognized academic databases—Springer, Scopus, IEEE Xplore, Web of Science, and EBSCOhost—covering the period from 2018 to 2024. The methodology adopted was based on Kitchenham’s (2009) guidelines, with detailed documentation of search equations, exclusion criteria, and quality assessment parameters to ensure the consistency, transparency, and reliability of the results obtained. The thematic analysis revealed that the categories "Intelligent Detection" and "Advanced Machine Learning" are particularly prominent in the scientific literature. Furthermore, it was observed that papers published in higher-quartile journals tend to offer conclusions with a greater degree of objectivity and methodological rigor. It is recommended to promote interdisciplinary studies that leverage the high frequency of co-authorship identified, thereby fostering stronger scientific collaboration networks. Likewise, the homogeneity observed in paper titles reveals consolidated thematic lines, opening opportunities to explore innovative approaches in the field of e-commerce and machine learning.