AI based strategic decision framework for precise e-commerce applications and ensuring consumer trust through tactical precision and decision-driven strategies

• CNNs detect counterfeit products with 90% accuracy and 95% recall. • Provides a roadmap for AI-based counterfeit detection implementation. • Enhances consumer trust and brand safety via AI-driven authenticity checks. • Explores AI’s future role in improving e-commerce security and reliability. The rapid rise of counterfeit products in the global marketplace has become a serious concern, leading to significant financial losses for businesses and safety risks for consumers. This study aims to develop a reliable and efficient framework for detecting counterfeit products, focusing on enhancing trust and authenticity within e-commerce platforms. The proposed approach utilizes image-based analysis through Convolutional Neural Networks (CNNs), strengthened by data augmentation and transfer learning to improve generalization and learning efficiency. The methodology encompasses stages of data acquisition, preprocessing, model development, and performance evaluation against traditional machine learning algorithms. Experimental results show that the CNN-based model achieves 90% accuracy and 95% recall, demonstrating its strong capability to distinguish between genuine and counterfeit items across diverse product categories. The findings highlight the potential of this approach to support brand protection and consumer confidence by providing a scalable and automated detection mechanism. The novelty of this work lies in integrating CNNs with data augmentation and transfer learning, resulting in a more adaptive, accurate, and practical solution for counterfeit detection in dynamic e-commerce environments.