Price spread prediction in high-frequency pairs trading using deep learning architectures
Jyh-Hwa Liou,
Yun-Ti Liu and
Li-Chen Cheng
International Review of Financial Analysis, 2024, vol. 96, issue PB
Abstract:
High-Frequency Trading (HFT) leverages advanced algorithms and high-speed data transmission to execute a large volume of trades within extremely short timeframes and generate profit. However, predicting stock prices in this context is challenging due to the frequent fluctuations in bid and ask conditions within financial markets. Institutional investors often employ pairs trading strategies to mitigate the systemic risk associated with single products, simultaneously buying and selling highly correlated financial instruments to profit from fluctuations in abnormal price spreads. In this study, we utilized intraday continuous trading data from the Taiwan Stock Exchange, integrating commonly used stock market features relevant to HFT. By employing XGBoost for feature selection and combining it with deep learning models, we aimed to predict the relationship between price spreads and boundaries in pairs trading, thereby generating entry and exit signals. Although accurately predicting the relationship between price spreads and boundaries presents significant challenges, the model effectively learned the pattern of price spread changes. Applying the model's entry and exit signals in pairs trading demonstrated that this strategy can enhance win rates and achieve stable profits in the volatile intraday market environment. This research provides practical implications for those interested in high-frequency trading and deep learning models in the financial market, equipping them with valuable knowledge and insights.
Keywords: High-frequency trading; Pairs trading; Deep learning; Feature selection; Price spread prediction (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/S1057521924007257
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:finana:v:96:y:2024:i:pb:s1057521924007257
DOI: 10.1016/j.irfa.2024.103793
Access Statistics for this article
International Review of Financial Analysis is currently edited by B.M. Lucey
More articles in International Review of Financial Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().