FinCast: A Foundation Model for Financial Time-Series Forecasting

TL;DR

FinCast is a pioneering foundation model for financial time-series forecasting that demonstrates robust zero-shot performance and outperforms existing methods across diverse financial domains and temporal resolutions.

Contribution

This paper introduces FinCast, the first foundation model tailored for financial time-series forecasting, addressing pattern shifts without extensive fine-tuning.

Findings

FinCast achieves superior zero-shot forecasting accuracy.

It generalizes well across multiple financial domains.

FinCast outperforms state-of-the-art methods in empirical evaluations.

Abstract

Financial time-series forecasting is critical for maintaining economic stability, guiding informed policymaking, and promoting sustainable investment practices. However, it remains challenging due to various underlying pattern shifts. These shifts arise primarily from three sources: temporal non-stationarity (distribution changes over time), multi-domain diversity (distinct patterns across financial domains such as stocks, commodities, and futures), and varying temporal resolutions (patterns differing across per-second, hourly, daily, or weekly indicators). While recent deep learning methods attempt to address these complexities, they frequently suffer from overfitting and typically require extensive domain-specific fine-tuning. To overcome these limitations, we introduce FinCast, the first foundation model specifically designed for financial time-series forecasting, trained on large-scale financial datasets. Remarkably, FinCast exhibits robust zero-shot performance, effectively capturing diverse patterns without domain-specific fine-tuning. Comprehensive empirical and qualitative evaluations demonstrate that FinCast surpasses existing state-of-the-art methods, highlighting its strong generalization capabilities.