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

TL;DR

This paper introduces a bipartite graph-based machine learning framework to predict Chinese market returns using U.S. market data, revealing significant directional predictive asymmetry.

Contribution

It presents a novel graph-structured feature selection method that captures cross-market dependencies while preserving economic interpretability.

Findings

U.S. previous-close returns predict Chinese intraday returns effectively.

Predictive asymmetry favors U.S. to Chinese market direction.

Structured models outperform unstructured approaches in forecasting accuracy.

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.