Optimizing Digital Shelf Space based on PCA-DT Machine Learning: Redefining E-commerce Merchandising and Product Visibility

Abstract

In the rapidly evolving e-commerce landscape, product visibility and effective shelf space management are crucial for enhancing customer engagement and driving sales. Traditional digital merchandising methods often struggle to keep up with the dynamic nature of online marketplaces and diverse consumer behaviors. This research proposes an innovative approach to optimizing digital shelf space using an implement advanced ML techniques like PCA and DT, -based machine learning model. By leveraging real-time data and customer interaction insights, the proposed model dynamically adjusts product placements to maximize visibility, click-through rates, and conversions. The integration of PCA-DT ensures the model’s robustness, efficiency, and ability to handle large datasets with high accuracy. Our experimental results demonstrate significant improvements in product discovery, customer satisfaction, and sales performance compared to conventional merchandising techniques. This research redefines e-commerce merchandising by providing a data-driven framework that adapts to market trends and user behavior, ultimately enhancing the efficiency and profitability of digital retail platforms.