Intelligent Routing for Sparse Demand Forecasting: A Comparative Evaluation of Selection Strategies

TL;DR

This paper introduces a Model-Router framework that dynamically selects the best forecasting model for each product's demand pattern, significantly improving accuracy and efficiency in sparse demand scenarios.

Contribution

It proposes a novel deep learning-based routing approach that adaptively chooses among classical, ML, and DL models for demand forecasting, outperforming single-model benchmarks.

Findings

Inception Time router improves accuracy by up to 11.8%.

Achieves 4.67x faster inference time.

Enhances supply chain efficiency by reducing stockouts and excess inventory.

Abstract

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.