Overview of Automated Keyword Selection Methods in Amazon Advertising Using Artificial Intelligence

Dmytro Balan

Citation: Dmytro Balan, "Overview of Automated Keyword Selection Methods in Amazon Advertising Using Artificial Intelligence", Universal Library of Innovative Research and Studies, Volume 02, Issue 01.

Copyright: This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

This paper provides a comprehensive overview of automated keyword selection techniques in Amazon Advertising that leverage artificial intelligence. It evaluates native tools—Search Term Report and Brand Analytics—as well as third-party services, identifying their limitations. Contemporary AI approaches are classified into three categories: natural language processing models (word2vec, BERT), clustering algorithms (K-means, DBSCAN), and predictive analytics methods (Random Forest, XGBoost). Building on this analysis, a dynamic optimization cycle—generation, testing, evaluation, retraining—is proposed to enable real-time model adaptation. The study’s novel contribution lies in the development of a unified taxonomy of AI methods for Amazon Advertising and an empirical comparative analysis of their effectiveness. The results equip small and medium-sized enterprises with strategies to allocate advertising budgets more efficiently and respond swiftly to shifts in consumer demand. Researchers in computational advertising management, particularly those working on semantic analysis and machine-learning-based campaign optimization, will find the classification and performance insights valuable. Digital marketing and e-commerce analytics professionals aiming to integrate advanced AI tools for improved targeting and budget management in Amazon Advertising will also benefit from these findings.


Keywords: Automated Keyword Selection, Amazon Advertising, Artificial Intelligence, NIP, Clustering, Predictive Analytics, ROI.

Download doi https://doi.org/10.70315/uloap.ulirs.2025.0201011