cs.AINov 7, 2026

TimeHF 2.0: Multimodal, Multivariate, and Multi-Region Collaborative Forecasting for Large-Scale Retail Supply Chains

Authors: Zhongxuan Han, Zhengxin Shi, Kunxiu Chen, Xiaolin Huang, Yulin Huang, Anni Zhang, Xiaoming Lin, Zhengyu Chen, 

Organizations: Supply Chain Tech Team Y, JD.com, China · Tsinghua University, China · Beijing Jiaotong University, China · The University of Hong Kong, China

Abstract

Large-scale retail supply chains need sales forecasts for specified products, future dates or planning windows, and regions under the conditions available at the forecast origin. Regional sparsity, changing environments, volatile sales, and unfamiliar business situations make these dimensions difficult to model together. We introduce TimeHF 2.0, a multimodal, multivariate, and multi-region collaborative forecasting framework that makes flexibly expressed business knowledge usable in numerical prediction. A coverage-aware directed encoder integrates regional sales and applicable covariates. A semantic alignment module transfers language-model hidden representations of natural-language plans and domain experience into target-specific forecasting context. Learning against sales observations connects these meanings to numerical evidence, allowing business users to supply experience, future plans, and changing circumstances without defining a new numerical feature for each description. Text-conditioned future queries and shared/routed experts adapt prediction to the supplied context. An ordered-distribution head allocates fine resolution to routine fluctuations and coarse resolution to extreme sales movements, while daily/window learning connects forecasts to cumulative planning quantities. Online parallel forecasting at JD yields relative accuracy improvements of 18.25% and 17.94% for national daily and planning-window sales, and 19.44% and 18.99% for DC daily and planning-window sales, over the original production deep learning baseline. Component comparisons, loss-design results, and product-type analyses examine the roles of regional information, covariates, business knowledge, context-dependent processing, and robust planning-oriented learning.

Figures & tables

Explore similar work

CardsList
  1. Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting

    May 28, 2026Haoxin Liu, Yichen Zhou, Rajat Sen +2Multivariate Time Series ForecastingLLM Post-Training

  2. Semantics-Enhanced Retrieval-Augmented Time Series Forecasting

    Jun 12, 2026Shiqiao Zhou, Zipeng Wu, Holger Schöner +3Time Series ForecastingNon-Stationary Time Series Forecasting