Forecasting Supply Chain Disruptions with Foresight Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Turtel, Benjamin, Wilczewski, Paul, Skotheim, Kris
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908931930980352
author Turtel, Benjamin
Wilczewski, Paul
Skotheim, Kris
author_facet Turtel, Benjamin
Wilczewski, Paul
Skotheim, Kris
contents Anticipating supply chain disruptions before they materialize is a core challenge for firms and policymakers alike. A key difficulty is learning to reason reliably about infrequent, high-impact events from noisy and unstructured inputs - a setting where general-purpose models struggle without task-specific adaptation. We introduce an end-to-end framework that trains LLMs to produce calibrated probabilistic forecasts using realized disruption outcomes as supervision. The resulting model substantially outperforms strong baselines - including GPT-5 - on accuracy, calibration, and precision. We also show that training induces more structured and reliable probabilistic reasoning without explicit prompting. These results suggest a general pathway for training domain-specific forecasting models that produce decision-ready signals. To support transparency we open-source the evaluation dataset used in this study. Dataset: https://huggingface.co/datasets/LightningRodLabs/supply-chain-predictions
format Preprint
id arxiv_https___arxiv_org_abs_2604_01298
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Forecasting Supply Chain Disruptions with Foresight Learning
Turtel, Benjamin
Wilczewski, Paul
Skotheim, Kris
Machine Learning
Anticipating supply chain disruptions before they materialize is a core challenge for firms and policymakers alike. A key difficulty is learning to reason reliably about infrequent, high-impact events from noisy and unstructured inputs - a setting where general-purpose models struggle without task-specific adaptation. We introduce an end-to-end framework that trains LLMs to produce calibrated probabilistic forecasts using realized disruption outcomes as supervision. The resulting model substantially outperforms strong baselines - including GPT-5 - on accuracy, calibration, and precision. We also show that training induces more structured and reliable probabilistic reasoning without explicit prompting. These results suggest a general pathway for training domain-specific forecasting models that produce decision-ready signals. To support transparency we open-source the evaluation dataset used in this study. Dataset: https://huggingface.co/datasets/LightningRodLabs/supply-chain-predictions
title Forecasting Supply Chain Disruptions with Foresight Learning
topic Machine Learning
url https://arxiv.org/abs/2604.01298