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

arXiv: https://arxiv.org/abs/2603.10559 · HTML: https://mlsanity.com/paper/2603.10559/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 54 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [A Review on Graph Neural Network Methods in Financial Applications](https://mlsanity.com/paper/2111.15367/) (2021)
- [ChatGPT Informed Graph Neural Network for Stock Movement Prediction](https://mlsanity.com/paper/2306.03763/) (2023)
- [Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction](https://mlsanity.com/paper/2310.05627/) (2023)
- [Multimodal Deep Learning for Finance: Integrating and Forecasting International Stock Markets](https://mlsanity.com/paper/1903.06478/) (2019)
- [The Physics of Financial Networks](https://mlsanity.com/paper/2103.05623/) (2021)
- [CSPO: Cross-Market Synergistic Stock Price Movement Forecasting with Pseudo-volatility Optimization](https://mlsanity.com/paper/2503.22740/) (2025)
- [Dynamic graph neural networks for enhanced volatility prediction in financial markets](https://mlsanity.com/paper/2410.16858/) (2024)

## Abstract (arXiv)

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.