Time Series Foundation Models for Multivariate Financial Time Series Forecasting

TL;DR

This paper evaluates Time Series Foundation Models (TSFMs) like Tiny Time Mixers and Chronos for financial forecasting, showing they improve data efficiency and transferability, especially in low-data scenarios, but may need domain-specific tuning.

Contribution

The study demonstrates the effectiveness of pretrained TSFMs in financial time series forecasting, highlighting their transferability, sample efficiency, and zero-shot capabilities across multiple tasks.

Findings

Pretrained TTM outperforms untrained models by 25-50% with limited data.

Zero-shot TTM surpasses naive benchmarks in volatility and spread prediction.

Pretrained models need 3-10 years less data to reach comparable performance.

Abstract

Financial time series forecasting presents significant challenges due to complex nonlinear relationships, temporal dependencies, variable interdependencies and limited data availability, particularly for tasks involving low-frequency data, newly listed instruments, or emerging market assets. Time Series Foundation Models (TSFMs) offer a promising solution through pretraining on diverse time series corpora followed by task-specific adaptation. This study evaluates two TSFMs (Tiny Time Mixers (TTM) and Chronos) across three financial forecasting tasks: US 10-year Treasury yield changes, EUR/USD volatility, and equity spread prediction. Results demonstrate that TTM exhibits strong transferability. When fine-tuning both the pretrained version of TTM and an untrained model with the same architecture, the pretrained version achieved 25-50% better performance when fine-tuned on limited data and 15-30% improvements even when fine-tuned on lengthier datasets. Notably, TTM's zero-shot performance outperformed naive benchmarks in volatility forecasting and equity spread prediction, with the latter demonstrating that TSFMs can surpass traditional benchmark models without fine-tuning. The pretrained model consistently required 3-10 fewer years of data to achieve comparable performance levels compared to the untrained model, demonstrating significant sample-efficiency gains. However, while TTM outperformed naive baselines, traditional specialised models matched or exceeded its performance in two of three tasks, suggesting TSFMs prioritise breadth over task-specific optimisation. These findings indicate that TSFMs, though still nascent, offer substantial promise for financial forecasting-particularly in noisy, data-constrained tasks-but achieving competitive performance likely requires domain-specific pretraining and architectural refinements tailored to financial time series characteristics.