Published Paper Details:

In the dynamic landscape of retail, the challenge of uncertain inventory decisions poses significant obstacles, leading to suboptimal stocking strategies, missed sales opportunities, and increased operational costs. This approach presents a novel approach to mitigate this challenge by integrating deep learning techniques, specifically convolutional neural networks (CNNs) implemented through Keras, with traditional machine learning algorithms such as Singular Value Decomposition (SVD). Leveraging image data, the CNN model accurately predicts demographic attributes like gender and age from customer images, augmenting the predictive capabilities of traditional methods. By harnessing these insights, retailers can optimize their inventory management strategies to stock items tailored to the preferences of diverse customer segments. The findings suggest that this integrated approach enhances inventory management efficiency, leading to improved customer satisfaction and cost savings. This approach contributes to advancing the state-of-the-art in retail inventory management, offering a promising avenue for retailers to adapt to evolving consumer demands in an increasingly competitive market