SOURCE-LINKED INTELLIGENCE

Evaluating Accuracy and Probabilistic Reliability of Zero-Shot Time Series Foundation Models

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Time Series Foundation Models (TSFMs) promise a paradigm shift toward zero-shot forecasting by eliminating task-specific training. However, existing works often overlook trade-offs between predictive accuracy and probabilistic calibration. This paper presents a benchmark study of six TSFMs evaluated on energy, traffic, and financial datasets. We contrast their performance against statistical baselines and a supervised DL model. The study reveals that while TSFMs outperform statistical methods and supervised models, they are subject to a fundamental trade-off between point accuracy and probabil

Read original source ↗ Open in workspace

recordType

paper

region

Global