面向金融世界模型：Market-1T 数据集与金融表征学习大规模研究

View PDF HTML (experimental)

Abstract:Building a world model requires a state representation useful for planning and decision-making---potentially over tasks unknown at training time. In the context of financial markets, planning and decision-making may require a model to reason about market-wide conditions, asset-specific expected returns, liquidity, volatility, and cross-asset relationships. Yet financial representation learning has largely been evaluated on individual predictive tasks, oftentimes on a single time period using comparatively narrow datasets. We address this through three primary contributions. First, we introduce Market-1T, a dataset containing nearly one trillion observations across U.S. equities from 2008 to 2025 at 1 Hz resolution. Second, we develop and implement a rigorous evaluation protocol. Third, we conduct a systematic large-scale study of financial representation learning, comparing 18 encoder-training strategies across nearly two decades of market regimes. We evaluate learned representations both by their predictive utility on common finance tasks and through probes of latent structure. We find that encoders with similar predictive performance can organize market state very differently. Collectively, we establish a foundation for training and evaluating financial market representations in support of world models such as DINO-WM, V-JEPA 2, and LeWM.

Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2610.09048 [cs.LG]
	(or arXiv:2610.09048v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.09048 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Bradford Levy [view email]
[v1] Tue, 6 Oct 2026 19:54:14 UTC (707 KB)