CrossAlpha: An Annual-Report Benchmark for Cross-Market Factor Research

2026-05-27

AI Summary

Existing public benchmarks struggle to support the evaluation of cross-market financial statement–to–earnings prediction due to challenges arising from linguistic differences, regulatory heterogeneity, disclosure biases, and misaligned trading timelines. This work introduces the first annual-report benchmark specifically designed for cross-market factor research, enabling standardized and comparable financial information across multiple languages and regulatory regimes through textual distillation and PCA whitening. It further proposes an evaluation framework based on residual pattern mapping and temporally aligned trading sequences. Spanning 3,600 firms across five markets, the benchmark yields approximately 19 million firm-pair similarity scores. In U.S.–Japan cross-market earnings prediction tasks, the proposed approach achieves a significantly higher information ratio compared to industry-code baselines and single-market textual models.

Abstract

Cross-market factor research studies whether firm-level signals from one or more markets can predict returns in a target market, but existing public benchmarks do not support cross-market disclosure-to-return evaluation. Building such a benchmark is challenging because filings differ across languages and regulatory systems, disclosure-derived similarity can be biased by common reporting components, and cross-market signals must be evaluated under feasible trading-time alignment. We introduce \textbf{CrossAlpha}, a public annual-report benchmark for cross-market factor research. CrossAlpha addresses these challenges through three corresponding components: \emph{Disclosure Distillation}, which standardises heterogeneous filings into ten-category English business descriptions; \emph{Residual Schema Graph Construction}, which builds PCA-whitened cross-market firm-pair scores from schema-level disclosures; and \emph{Timing-Aligned Evaluation}, which pairs the graph with 11 years of daily OHLCV data to construct forward-return labels under feasible cross-market execution protocols. CrossAlpha covers about 3,600 firms and 10,700 firm-year reports from the United States, Japan, Taiwan, South Korea, and Hong Kong, and releases about 19M directed firm-pair scores. In experiments, disclosure-derived cross-market peers outperform domestic text, industry-code, and return-correlation peers in the US-to-Japan setting (ICIR 0.39 versus 0.07--0.18), and cross-market sources beat the domestic text baseline in most target markets. CrossAlpha offers an open-sourced, reusable, return-grounded benchmark for cross-market financial NLP.

Problem

• cross-market factor research
• annual-report benchmark
• disclosure-to-return evaluation
• financial NLP
• trading-time alignment

Innovation

• Cross-market factor research
• Disclosure Distillation
• Residual Schema Graph
• Timing-Aligned Evaluation
• Financial NLP