A Bipartite Graph Approach to U.S.-China Cross-Market Return Forecasting

2026-03-11

AI Summary

This study investigates the predictability of cross-market returns between U.S. and Chinese equity markets, with a focus on forecasting intraday Chinese stock returns using information from non-overlapping U.S. trading hours. The authors propose a structured machine learning framework that integrates economic priors: a directed bipartite graph encodes temporal predictive relationships, while a rolling-window hypothesis testing procedure selects sparse, economically interpretable features; these are then combined with regularization and ensemble methods for prediction. Empirical results reveal that U.S. close-to-close returns from the prior trading day contain significant predictive power for Chinese intraday returns, whereas the reverse effect is negligible, indicating pronounced information asymmetry. This directional predictability translates into economically meaningful improvements in out-of-sample forecasting performance.

Technology Category

• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Relational Probabilistic Models
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Economics, Online Markets and Human Computation: Social networks and social learning
• Web Mining and Content Analysis: Machine learning and data science for the Web
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

This paper studies cross-market return predictability through a machine learning framework that preserves economic structure. Exploiting the non-overlapping trading hours of the U.S. and Chinese equity markets, we construct a directed bipartite graph that captures time-ordered predictive linkages between stocks across markets. Edges are selected via rolling-window hypothesis testing, and the resulting graph serves as a sparse, economically interpretable feature-selection layer for downstream machine learning models. We apply a range of regularized and ensemble methods to forecast open-to-close returns using lagged foreign-market information. Our results reveal a pronounced directional asymmetry: U.S. previous-close-to-close returns contain substantial predictive information for Chinese intraday returns, whereas the reverse effect is limited. This informational asymmetry translates into economically meaningful performance differences and highlights how structured machine learning frameworks can uncover cross-market dependencies while maintaining interpretability.

Problem

• cross-market return predictability
• U.S.-China equity markets
• non-overlapping trading hours
• predictive linkages
• informational asymmetry

Innovation

• bipartite graph
• cross-market predictability
• structured machine learning
• economic interpretability
• information asymmetry