Allocating products in retail stores poses an interesting challenge for retailers in which space, productivity, and business contexts must all be acknowledged when making decisions on what to provide customers during in-store experiences. It aims to increase revenue and provide a better in-store experience for customers by placing the most productive and sought after products on the shelves. It also aims to aid in inventory management practices by offering suggestions for higher productivity SKUs. This project analyzes the sales data of vendors in the same class of products to optimize the in-store assortment and provide suggestions for the next steps to improve business practices. An XGBoost Regression model is created that aids in forecasting product sales with increased store presence for SKUs that are lacking in-store sales data. These forecasts and then fed into an Operations Research model that selects and allocates products to be in stores based on their fit on the planogram as well as their productivity to maximize possible revenue. The results are then synthesized and interpreted for the usage of decision makers while highlighting the use cases for machine learning and data science to aid in optimizing workflows. It then provides suggestions for business leaders and decision makers and provides context to support its suggestions when negotiating with vendors over store space.