{"ID":2838083,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18578","arxiv_id":"2511.18578","title":"Re(Visiting) Time Series Foundation Models in Finance","abstract":"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.","short_abstract":"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 generaliza...","url_abs":"https://arxiv.org/abs/2511.18578","url_pdf":"https://arxiv.org/pdf/2511.18578v1","authors":"[\"Eghbal Rahimikia\",\"Hao Ni\",\"Weiguan Wang\"]","published":"2025-11-23T18:44:19Z","proceeding":"q-fin.CP","tasks":"[\"q-fin.CP\",\"cs.AI\",\"cs.LG\",\"q-fin.PM\",\"q-fin.PR\"]","methods":"[\"Language Model\"]","has_code":false}