Score: 2

Re(Visiting) Time Series Foundation Models in Finance

Published: November 23, 2025 | arXiv ID: 2511.18578v1

By: Eghbal Rahimikia, Hao Ni, Weiguan Wang

Potential Business Impact:

Teaches computers to predict stock prices better.

Business Areas:
Prediction Markets Financial Services

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.

Country of Origin
🇨🇳 🇬🇧 China, United Kingdom

Repos / Data Links

Page Count
138 pages

Category
Quantitative Finance:
Computational Finance