New AI Model Improves Supply Chain Lead Time Forecasting

Researchers have developed LeadTime-ICL (LT-ICL), a novel in-context learning model designed for probabilistic forecasting of supplier lead times, particularly in scenarios with right-censored data. This model utilizes a transformer backbone and a conditional normalizing-flow head to predict a full distribution of lead times, overcoming limitations of traditional regression and survival models. Pretrained on synthetic data, LT-ICL demonstrates strong performance across 24 industrial supply chain datasets, outperforming existing methods in both point and probabilistic forecasting accuracy. AI

IMPACT This model could significantly improve supply chain efficiency and risk management by providing more accurate lead time predictions.

RANK_REASON The cluster contains a research paper detailing a new AI model and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• LeadTime-ICL
• Litmaps
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
• ScienceCast
• scite Smart Citations
• Transformer++

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →