Signature Decomposition Method Applying to Pair Trading

Zihao Guo, Hanqing Jin, Jiaqi Kuang, Zhongmin Qian and Jinghan Wang

Papers from arXiv.org

Abstract: Quantitative trading strategies based on medium- and high-frequency data have long been of significant interest in the futures market. The advancement of statistical arbitrage and deep learning techniques has improved the ability of processing high-frequency data, but also reduced arbitrage opportunities for traditional methods, yielding strategies that are less interpretable and more unstable. Consequently, the pursuit of more stable and interpretable quantitative investment strategies remains a key objective for futures market participants. In this study, we propose a novel pairs trading strategy by leveraging the mathematical concept of path signature which serves as a feature representation of time series data. Specifically, the path signature is decomposed to create two new indicators: the path interactivity indicator segmented signature and the change direction indicator path difference product. These indicators serve as double filters in our strategy design. Using minute-level futures data, we demonstrate that our strategy significantly improves upon traditional pairs trading with increasing returns, reducing maximum drawdown, and enhancing the Sharpe ratio. The method we have proposed in the present work offers greater interpretability and robustness while ensuring a considerable rate of return, highlighting the potential of path signature techniques in financial trading applications.

Date: 2025-05
New Economics Papers: this item is included in nep-mst
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://arxiv.org/pdf/2505.05332 Latest version (application/pdf)

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:arx:papers:2505.05332

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().