Intelligent Routing for Sparse Demand Forecasting: A Comparative Evaluation of Selection Strategies
This addresses inventory management challenges for supply chain operations, though it is incremental as it builds on existing routing and forecasting methods.
The paper tackles sparse demand forecasting in supply chains by proposing a Model-Router framework that dynamically selects forecasting models based on product demand patterns, achieving up to 11.8% accuracy improvement and 4.67x faster inference time on the Favorita dataset.
Sparse and intermittent demand forecasting in supply chains presents a critical challenge, as frequent zero-demand periods hinder traditional model accuracy and impact inventory management. We propose and evaluate a Model-Router framework that dynamically selects the most suitable forecasting model-spanning classical, ML, and DL methods for each product based on its unique demand pattern. By comparing rule-based, LightGBM, and InceptionTime routers, our approach learns to assign appropriate forecasting strategies, effectively differentiating between smooth, lumpy, or intermittent demand regimes to optimize predictions. Experiments on the large-scale Favorita dataset show our deep learning (Inception Time) router improves forecasting accuracy by up to 11.8% (NWRMSLE) over strong, single-model benchmarks with 4.67x faster inference time. Ultimately, these gains in forecasting precision will drive substantial reductions in both stockouts and wasteful excess inventory, underscoring the critical role of intelligent, adaptive Al in optimizing contemporary supply chain operations.