A Distributionally Robust Optimization Approach to Quick Response Models under Demand Uncertainty

Abstract: Problem definition: Quick response, a strategy widely adopted to mitigate overproduction in the retail industry, is now at the center of a critical debate. Recent research reveals a counter-intuitive paradox: while quick response systems reduce waste from unsold finished goods, they may incentivize firms to procure more raw materials, potentially increasing total system waste. Additionally, existing models that guide quick response strategies rely on the assumption of a known demand distribution. In practice, demand patterns are complex and ambiguous, and historical data is often scarce, leaving managers without a reliable framework to determine quick response policies under data-driven settings. Methodology: We develop a distributionally robust quick response model to address demand uncertainty, building policies that are robust even with limited data. We further integrate a novel waste-to-consumption ratio constraint into this framework, empowering firms to explicitly control the environmental impact of quick response systems. Results: Numerical experiments show that policies optimized for a specific demand assumption suffer severe performance degradation when the real demand pattern changes even slightly. In contrast, our data-driven DRO approach consistently delivers robust and superior performance across a wide range of complex demand distributions. Moreover, we find that the constrained quick response model resolves the central paradox: it can achieve higher profits with verifiably less total waste than a traditional, non-flexible alternative. Managerial implications: Our research resolves the quick response or not' debate by showing that the question is not whether to use quick response, but how to manage it. By incorporating socially responsible metrics as constraints, the quick response system delivers awin-win' outcome for both profitability and the environment.