Data-driven time-varying discrete grey model for demand forecasting
提出一种时变离散灰色模型，通过数据驱动算法自动识别最优结构，在真实零售销售数据上优于统计和AI方法，适用于商业需求预测。
Demand forecasting is critical for strategic decision-making in the business sector. However, estimating demand variations remains challenging due to their time-varying tendencies. To address this, we propose a novel universal approach called the time-varying discrete grey model, along with a data-driven model structure identification algorithm. Specifically, we introduce a universal model form that incorporates polynomial time-varying parameters to unify existing discrete grey models. We then discuss significant properties, such as unbiasedness and affine transformation. Furthermore, we develop a data-driven algorithm that adaptively identifies the optimal model structure via subset selection strategies. To validate the effectiveness of our approach, we conduct Monte Carlo simulations to assess its robustness against noise and evaluate its performance in multi-step-ahead forecasting. Finally, through extensive experiments on real-world datasets from USA State Retail Sales, we demonstrate the superiority of our model over benchmark approaches, including statistical models and artificial intelligence methods. Our proposed approach offers a competitive alternative for demand forecasting in the business sector.