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

Zhongxuan Han, Zhengxin Shi, Kunxiu Chen, Xiaolin Huang, Yulin Huang, Anni Zhang, Xiaoming Lin, Zhengyu Chen, Xue Yu, Yang Liu, Yuanyuan Yang, Yangyang Zhang, Junheng Huang, Dongyang Geng, Ben Zhang, Xin Wang, Jiaxin Wang, Haowei Zhou, Qiqi Yan, Jiaheng Yin, Jintao Xu, Zijiang Liu, Changfei Zhan, Yutong Pan, Jinqiu Deng, Shaomin Li, Ningxuan Kang, Jianshen Zhang, Yongzhi Qi, Wei Qi, Dazhou Lei, Zuo-Jun Max ShenarXiv 2026 · arXiv

TL;DR

TimeHF 2.0 is a next-generation forecasting framework that integrates numerical time-series data with natural-language business insights (like promotional plans or domain expertise). By combining a coverage-aware regional encoder with LLM-based semantic alignment, it achieves an ~18-19% accuracy improvement over production baselines for JD.com’s massive retail supply chain.

What Problem Does This Paper Address?

Large-scale retail forecasting is notoriously difficult due to "cold starts" for new products, regional data sparsity, and extreme sales volatility. Traditional models rely heavily on historical numerical features, but they often miss the "why" behind the data. For instance, if a manager knows a specific "back-to-school" campaign is starting, that knowledge is often trapped in a text document or a human's head rather than a structured database.

The authors identify five core challenges (C1–C5) in this domain:

  1. Regional Heterogeneity: Local distribution centers (DCs) have different patterns than national averages.
  2. Variable Availability: Some data (like weather) is only known at the forecast origin, while other data (like page views) is historical.
  3. Demand Regimes: Products shift between stable, seasonal, and promotion-driven states.
  4. Planning vs. Precision: Supply chains need both daily accuracy and cumulative totals for procurement windows.
  5. Unfamiliar Situations: Models struggle when faced with new events that have no historical numerical precedent.
Figure 2 illustrates these five challenges, ranging from regional variation to the need for flexible business knowledge.

Methods

TimeHF 2.0 moves beyond simple sequence-to-sequence models by introducing a multimodal, multi-series architecture.

  • Directed Encoder: Instead of a standard Transformer encoder, it uses "directed variable attention." This allows the model to selectively transfer patterns from national or peer-DC histories to a specific local target based on "coverage context" (e.g., service area size and city relevance).
  • Semantic Alignment: This is the "secret sauce." The model uses a Large Language Model (LLM) to process natural-language descriptions of plans and experiences. A trainable alignment module then maps these linguistic representations into the same vector space as the numerical sales data.
  • Text-Conditioned Decoder: The decoder uses a Mixture of Experts (MoE) approach. The "experts" (specialized sub-networks) are activated based on the context provided by the text. If the text describes a "promotion lead-in," the model routes the computation to experts trained for high-volatility regimes.
  • Ordered-Distribution Head: Rather than predicting a single point estimate, the model predicts a probability distribution over "ordered bins." It uses fine-grained bins for routine fluctuations and coarse bins for extreme peaks, making the model more robust to outliers.
The TimeHF 2.0 framework connects numerical encoding, text alignment, and parallel decoding.

Datasets

The model was evaluated using JD.com’s industrial-scale retail data:

  • Scale: 200,000 SKUs across hundreds of distribution centers.
  • Training Corpus: 912 billion data points sampled from 2023–2025.
  • Evaluation Period: January–September 2026 (online parallel forecasting).
  • Inputs: Origin-visible sales histories, structured covariates (weather, page views), and natural-language business descriptions.

Key Insights and Ideas

  • Language as a "Soft" Feature: The most striking idea is that text isn't just a label; it's a condition. By describing a campaign in prose, users can influence the forecast without needing to engineer a new numerical feature for every unique event.
  • Robustness through Binning: By using non-uniform bins for the output, the model avoids being "pulled" too hard by unpredictable bulk orders (outliers) while still capturing the sustained "lift" from a planned promotion.
  • Regional Collaboration: The model proves that "national" data is a powerful regularizer for "local" DC data, provided the model has a mechanism (the directed encoder) to ignore irrelevant regional signals.
Figure 4 shows how the model distinguishes between "supported lift" from a promotion and "uncontrolled bursts" like one-off bulk orders.

Key Results

The framework was tested in a live "online parallel" setting at JD.com, comparing it against a deep learning production baseline:

  • National Level: Relative accuracy improved by 18.25% for daily sales and 17.94% for planning windows.
  • DC Level: Even higher gains, with 19.44% improvement for daily and 18.99% for windows.
  • Product Types: The model was particularly effective for "Long-tail" and "Seasonal" products at the DC level, where data is usually sparsest.
  • Ablation Studies: Removing the multimodal (text) component led to a measurable drop in performance, confirming that business knowledge provides a unique signal that numerical history cannot.

Limitations and Future Work

Despite the gains, the authors note that "abrupt local peaks" and "ambiguous plans" still pose challenges. For example, if a user provides a vague description of a plan, the model's response may be less accurate.

The roadmap for the future is TimeHF 3.0, which aims for "native multimodal-to-multimodal" modeling. The goal is to move beyond just taking text as input to providing native explanations—where the model doesn't just give a forecast but explains in natural language why it changed the prediction based on the provided context.

Summary updated

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.
BibTeX
@misc{han2026timehf,
  author = {Zhongxuan Han and Zhengxin Shi and Kunxiu Chen and Xiaolin Huang and Yulin Huang and Anni Zhang and Xiaoming Lin and Zhengyu Chen and Xue Yu and Yang Liu and Yuanyuan Yang and Yangyang Zhang and Junheng Huang and Dongyang Geng and Ben Zhang and Xin Wang and Jiaxin Wang and Haowei Zhou and Qiqi Yan and Jiaheng Yin and Jintao Xu and Zijiang Liu and Changfei Zhan and Zhe Chen and Yutong Pan and Jinqiu Deng and Shaomin Li and Ningxuan Kang and Jianshen Zhang and Yongzhi Qi and Wei Qi and Dazhou Lei and Zuo-Jun Max Shen},
  title = {{TimeHF 2.0: Multimodal, Multivariate, and Multi-Region Collaborative Forecasting for Large-Scale Retail Supply Chains}},
  year = {2026},
  eprint = {2611.10521},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.10521},
}

Loading related content...

Figure