From Strategy to Execution: An Optimization Approach to New Product Placement in the Apparel Industry

Abstract

This thesis presents the development and implementation of a new product placement optimization model for a large global apparel and footwear company’s supply chain, aimed at maximizing network-wide profits while aligning with long-term strategic goals amidst demand volatility. The model leverages a mixed-integer linear programming approach, integrating probabilistic demand simulations to optimize the placement of new products within the company’s existing network of third-party partner company factories. Key elements of the model, including decision variables, price and cost coefficients, an objective function, and constraints that reflect operational realities and strategic priorities, are discussed in detail. Through analysis and results validation, this research demonstrates how data-driven optimization can improve network profitability and adherence to companies’ long-term strategic supply chain objectives and develop networks that are more profitable. The thesis then includes an exploration of historic demand variability at the host company, followed by a recommendation to integrate probabilistic forecasting in network planning to generate production networks more robust to volatility in consumer product demand. The findings contribute to advancing data-driven decision-making in supply chain management and offer actionable insights for future product placement strategies.