Inventory management is one of the main operational challenges in the retail industry. Often, when a retailer reports disappointing financial results, poor inventory planning is often singled out as the largest culprit for subpar margins. As brick-and-mortar retailers have expanded into the digital realm, this challenge has become even more acute. Planning inventory weeks in advance is a delicate problem, balancing the risks of lost sales and markdowns against excess carrying and shipping costs. It's also necessary to account for a wide range of variables, from internal factors like marketing spend, supply chain dynamics, and contractual obligations to external influences like weather and consumer spending patterns. Traditional approaches, like fixed reorder quantity systems, are still in widespread use despite being inadequate to solve this problem in the modern retail environment. At Pacific Data Science, we excel at solving this type of complex optimization problem, integrating our expertise in time series prediction, search algorithms, and reinforcement learning.