This project revolves around an optimization model that will streamline pricing for a national parts supplier. Historically, pricing had been a messy and labor-intensive process with price points scattered across an unnecessarily wide range of values. The organization has requested that a unique maximum and minimum sale price be generated for each of the more than one million products that are offered. Together, each maximum and minimum will form a pricing band that will keep all sales constrained to that specific region. The four-part predictive pricing model is comprised of a data pull, an initial optimization, missing data imputation via KNN and linear regression, and a genetic algorithm based final optimization. The model will be built using three distinct product groupings, comprising roughly 2,000 total products. Internal sales data and competitor pricing data will serve as the model input. Optimized maximums and minimums for each product will encompass the model output. Overall, the predictive pricing model could launch the company pricing structure into the future by providing fast, accurate, and individualized pricing bands that could serve as a template for other organizations to follow.