Multivariate Financial Forecasting using the Chronos Time Series Foundation Models

2026-05-08 · Sanjiv R Das, Tarang Goyal, Mohini Yadav arxiv

Using Chronos-2, an open-source time-series foundation model, we evaluate pretrained time-series models for economic and financial forecasting with an emphasis on whether multivariate (MV) inputs improve accuracy relative to univariate (UV) baselines. The study covers two panels -- the Magnificent-7 equities and U.S. Treasury interest rates -- as well as a combined panel, using rolling monthly evaluations from 2000--2025. We vary input window lengths and forecast horizons and report RMSE and MAPE. Across datasets, MV forecasts consistently outperform UV forecasts, with especially strong gains for interest rates and meaningful improvements for equities. Series-level comparisons show MV improvements in every case, and error dispersion is generally lower under MV inputs. We also provide parameter-heatmap and time-series visualizations. However, mixing time series across equity and interest rate markets reduces forecast accuracy, indicating that adding noisy context degrades model performance. Overall, the results indicate that foundation models can leverage cross-series information to improve forecast accuracy in finance, and that the benefits are strongest when related series are modeled jointly under disciplined rolling protocols. Other than using an open-source foundation model, this paper also showcases how AI may be used for financial research.

📄 PDF Abstract BibTeX arXiv:2605.21504

Code (0)

등록된 구현이 없습니다.

Chronos-2: From Univariate to Universal Forecasting

2025-10-17 · Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken, Andreas Auer 외 arxiv

Pretrained time series models have enabled inference-only forecasting systems that produce accurate predictions without task-specific training. However, existing approaches largely focus on univariate forecasting, limiti…

Time Series Foundation Models for Multivariate Financial Time Series Forecasting

2025-07-09 · Ben A. Marconi arxiv

Financial time series forecasting presents significant challenges due to complex nonlinear relationships, temporal dependencies, variable interdependencies and limited data availability, particularly for tasks involving …

Time Series Forecasting

Chronos: Learning the Language of Time Series

2024-03-12 · Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang 외

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing tran…

Gaussian Processes Language Modeling Language Modelling Quantization+1

Forecasting in multivariate irregularly sampled time series with missing values

2020-04-06 · Shivam Srivastava, Prithviraj Sen, Berthold Reinwald

Sparse and irregularly sampled multivariate time series are common in clinical, climate, financial and many other domains. Most recent approaches focus on classification, regression or forecasting tasks on such data. In …

General Classification Irregular Time Series Missing Values regression+2

Empirical evaluation of Time Series Foundation Models for Day-ahead and Imbalance Electricity Price Forecasting in Belgium

2026-05-16 · Chi Bui, Maria Margarida Mascarenhas, Arnaud Verstraeten, Hussain Kazmi arxiv

Recent advances in Time Series Foundation Models (TSFMs) promise zero-shot forecasting capabilities with minimal task-specific training. While these models have shown strong performance across generic benchmarks, their a…