Published Paper Details:

In today's data-driven retail environment, accurately forecasting profits and understanding customer behavior are vital for strategic decision-making. This project presents an integrated AI-powered framework for profit prediction and behavioral clustering in retail, leveraging the capabilities of deep learning models. A neural network-based regression model is developed to predict retail profit using historical sales, customer, and product data. To enhance the interpretability of the model, SHAP (SHapley Additive exPlanations) values are used to explain feature contributions, enabling actionable business insights. For customer segmentation, the project utilizes autoencoders to extract latent features from high-dimensional behavioral data, followed by clustering techniques to identify distinct customer profiles. This dual approach not only improves forecasting accuracy but also aids in personalized marketing and inventory optimization. The system is deployed using Streamlit, offering an interactive and user-friendly interface for stakeholders. The proposed solution demonstrates the potential of deep learning in transforming retail analytics through predictive modeling and intelligent customer segmentation.