A self-attention based cross-sectional return forecasting model with evidence from the Chinese market

Xiang Xiao, Xia Hua and Kexin Qin

Finance Research Letters, 2024, vol. 62, issue PA

Abstract: This study introduces a novel model based on self-attention mechanisms to generate out-of-sample forecasts of cross-sectional returns. This model is designed to capture the non-linearity, heterogeneity, and interaction between stocks inherent in cross-sectional pricing problems. The empirical results from the Chinese stock market reveal compelling findings, surpassing other benchmarks in terms of out-of-sample R2. Moreover, this model demonstrates both practical applicability and robustness. These results provide valuable evidence supporting the existence of the three aforementioned properties in cross-sectional pricing problems from a theoretical standpoint, and this model offers a powerful tool for implementing profitable long-short strategies.

Keywords: Self-attention; Cross-sectional models; Asset pricing; Stock market (search for similar items in EconPapers)
JEL-codes: C31 G11 G12 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612324001740
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:finlet:v:62:y:2024:i:pa:s1544612324001740

DOI: 10.1016/j.frl.2024.105144

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().