LOBIN: in-network machine learning for limit order books

Conference item

Machine learning is driving the evolution of algorithmic trading, but the demands for fast execution speed remain. Although both aim to increase profitability, embedding more powerful machine learning approaches and lowering trading latencies are hard to achieve simultaneously. Offloading machine learning inference to programmable network devices, also referred to as in-network machine learning, provides a delicate balance between the two ends of this trade-off. In this paper, we present LOBIN, providing machine learning based market prediction using high-frequency market data feeds. LOBIN builds limit order books and conducts inference within programmable switches. Compared with server-based solutions, LOBIN predicts future stock price movements with lower latency, higher throughput, and a minor impact on machine learning performance.

Authors: Hong, X; Zheng, C; Zohren, S; Zilberman, N

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Host title: 2023 IEEE 24th International Conference on High Performance Switching and Routing (HPSR)
• Journal: 2023 IEEE 24th International Conference on High Performance Switching and Routing (HPSR)
• Pages: 159-166
• Publication date: 2023-06-14
• Acceptance date: 2023-04-11
• Event title: IEEE 24th International Conference on High-Performance Switching and Routing (IEEE HPSR 2023)
• Event location: Albuquerque, New Mexico, USA
• Event website: https://hpsr2023.ieee-hpsr.org/
• Event start date: 2023-06-05
• Event end date: 2023-06-07
• DOI: 10.1109/HPSR57248.2023.10147958
• EISSN: 2325-5609
• ISSN: 2325-5595
• EISBN: 9781665476409
• ISBN: 9781665476416
• Language: English
• Keywords: machine learning; in-network computing; time series prediction; limit order books; P4; programmable switches; microstructure market data