# Re(Visiting) Time Series Foundation Models in Finance

arXiv: https://arxiv.org/abs/2511.18578 · HTML: https://mlsanity.com/paper/2511.18578/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2025.

## Built on by (most cited first, 7 of 7)

- [TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models](https://mlsanity.com/paper/2605.26161/) (2026)
- [Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting](https://mlsanity.com/paper/2602.01736/) (2026)
- [OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents](https://mlsanity.com/paper/2606.26350/) (2026)
- [Forecast Collapse in Time-Series Foundation Models](https://mlsanity.com/paper/2608.14106/) (2026)
- [VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling](https://mlsanity.com/paper/2607.13929/) (2026)
- [A Unified Scaling Law for Time Series Foundation Models](https://mlsanity.com/paper/2610.05269/) (2026)
- [Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction](https://mlsanity.com/paper/2610.07825/) (2026)

## Abstract (arXiv)

Financial time series forecasting is central to trading, portfolio optimization, and risk management, yet it remains challenging due to noisy, non-stationary, and heterogeneous data. Recent advances in time series foundation models (TSFMs), inspired by large language models, offer a new paradigm for learning generalizable temporal representations from large and diverse datasets. This paper presents the first comprehensive empirical study of TSFMs in global financial markets. Using a large-scale dataset of daily excess returns across diverse markets, we evaluate zero-shot inference, fine-tuning, and pre-training from scratch against strong benchmark models. We find that off-the-shelf pre-trained TSFMs perform poorly in zero-shot and fine-tuning settings, whereas models pre-trained from scratch on financial data achieve substantial forecasting and economic improvements, underscoring the value of domain-specific adaptation. Increasing the dataset size, incorporating synthetic data augmentation, and applying hyperparameter tuning further enhance performance.