AI RESEARCH

Taxonomy-Conditioned Hierarchical Bayesian TSB Models for Heterogeneous Intermittent Demand Forecasting

arXiv CS.LG

ArXi:2511.12749v2 Announce Type: replace-cross Intermittent demand forecasting poses unique challenges due to sparse observations, cold-start items, and obsolescence. Classical models such as Croston, SBA, and the Teunter--Syntetos--Babai (TSB) method provide simple heuristics but lack a principled generative foundation. We