# Performance of Zero-Shot Time Series Foundation Models on Cloud Data

arXiv: https://arxiv.org/abs/2502.12944 · HTML: https://mlsanity.com/paper/2502.12944/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 17 of 17)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation](https://mlsanity.com/paper/2410.10393/) (2024)
- [Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series](https://mlsanity.com/paper/2401.03955/) (2024)
- [VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2408.17253/) (2024)
- [TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2410.11802/) (2024)
- [An Analysis of Linear Time Series Forecasting Models](https://mlsanity.com/paper/2403.14587/) (2024)
- [Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2405.02358/) (2024)
- [Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models](https://mlsanity.com/paper/2410.09385/) (2024)
- [How Does It Function? Characterizing Long-term Trends in Production Serverless Workloads](https://mlsanity.com/paper/2312.10127/) (2023)
- [DAM: Towards A Foundation Model for Time Series Forecasting](https://mlsanity.com/paper/2407.17880/) (2024)
- [Serverless Cold Starts and Where to Find Them](https://mlsanity.com/paper/2410.06145/) (2024)

## Built on by (most cited first, 10 of 10)

- [This Time is Different: An Observability Perspective on Time Series Foundation Models](https://mlsanity.com/paper/2505.14766/) (2025)
- [True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics](https://mlsanity.com/paper/2505.13192/) (2025)
- [TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis](https://mlsanity.com/paper/2510.06063/) (2025)
- [One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo](https://mlsanity.com/paper/2509.04208/) (2025)
- [Why Cannot Neural Networks Master Extrapolation? Insights from Physical Laws](https://mlsanity.com/paper/2510.04102/) (2025)
- [Adapting Time Series Foundation Models through Data Mixtures](https://mlsanity.com/paper/2603.02840/) (2026)
- [BinConv: A Neural Architecture for Ordinal Encoding in Time-Series Forecasting](https://mlsanity.com/paper/2505.24595/) (2025)
- [CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation](https://mlsanity.com/paper/2606.13513/) (2026)
- [A Later Test Set Is Not a New Domain: Pretraining Familiarity Survives a Contamination-Free Hold-Out](https://mlsanity.com/paper/2609.10357/) (2026)
- [Evaluating Accuracy and Probabilistic Reliability of Zero-Shot Time Series Foundation Models](https://mlsanity.com/paper/2609.25788/) (2026)

## Abstract (arXiv)

Time series foundation models (FMs) have emerged as a popular paradigm for zero-shot multi-domain forecasting. FMs are trained on numerous diverse datasets and claim to be effective forecasters across multiple different time series domains, including cloud data. In this work we investigate this claim, exploring the effectiveness of FMs on cloud data. We demonstrate that many well-known FMs fail to generate meaningful or accurate zero-shot forecasts in this setting. We support this claim empirically, showing that FMs are outperformed consistently by simple linear baselines. We also illustrate a number of interesting pathologies, including instances where FMs suddenly output seemingly erratic, random-looking forecasts. Our results suggest a widespread failure of FMs to model cloud data.