Search papers, labs, and topics across Lattice.
The paper introduces Anti-CrossTalk (ACT), a novel framework for cross-sectional stock ranking that addresses the problem of crosstalk, or unintended information interference, in existing deep learning models. ACT mitigates temporal-scale crosstalk by decomposing stock sequences into trend, fluctuation, and shock components and processing them separately, and it reduces structural crosstalk using a Progressive Structural Purification Encoder. Experiments on CSI300 and CSI500 datasets demonstrate that ACT achieves state-of-the-art ranking accuracy and portfolio performance, significantly outperforming existing methods.
Achieve up to 74% improvement in stock ranking accuracy by disentangling temporal trends and purifying structural relationships, sidestepping the crosstalk problem that plagues existing graph-based methods.
Cross-sectional stock ranking is a fundamental task in quantitative investment, relying on both temporal modeling of individual stocks and the capture of inter-stock dependencies. While existing deep learning models leverage graph-based approaches to enhance ranking accuracy by propagating information over relational graphs, they suffer from a key challenge: crosstalk, namely unintended information interference across predictive factors. We identify two forms of crosstalk: temporal-scale crosstalk, where trends, fluctuations, and shocks are entangled in a shared representation and non-transferable local patterns contaminate cross-stock learning; and structural crosstalk, where heterogeneous relations are indiscriminately fused and relation-specific predictive signals are obscured. To address both issues, we propose the Anti-CrossTalk (ACT) framework for cross-sectional stock ranking via temporal disentanglement and structural purification. Specifically, ACT first decomposes each stock sequence into trend, fluctuation, and shock components, then extracts component-specific information through dedicated branches, which effectively decouples non-transferable local patterns. ACT further introduces a Progressive Structural Purification Encoder to sequentially purify structural crosstalk on the trend component after mitigating temporal-scale crosstalk. An adaptive fusion module finally integrates all branch representations for ranking. Experiments on CSI300 and CSI500 demonstrate that ACT achieves state-of-the-art ranking accuracy and superior portfolio performance, with improvements of up to 74.25% on the CSI300 dataset.
