Accelerating machine learning for trading using programmable switches

Conference item

High-frequency trading (HFT) employs cutting-edge hardware for rapid decision-making and order execution but often relies on simpler algorithms that may miss deeper market trends. Conversely, lower-frequency algorithmic trading uses machine learning (ML) for better market predictions but higher latency can negate its strategic benefits. To achieve the best of both worlds, we present an in-network ML solution that embeds ML processes into programmable network devices, accelerating feature engineering and extraction as well as ML inference. In this paper, we design and develop a solution that supports both stock mid-price and volatility movement forecasting using commodity switches. Our approach achieves microsecond-scale, ultra-low latency, significantly lowering it by 64% to 97% compared to previous works, while upholding the same level of ML performance as server models. Additionally, by combining network hardware and servers, a hybrid deployment strategy can keep the misclassification rate change below 0.8% relative to the server baseline while processing 49% of the traffic directly on the switch and achieving a 45% average reduction in end-to-end latency.

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

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IOS Press
• Host title: ECAI 2024
• Pages: 3429-3436
• Series: Frontiers in Artificial Intelligence and Applications
• Series number: 392
• Publication date: 2024-10-16
• Acceptance date: 2024-07-04
• Event title: 27th European Conference on Artificial Intelligence (ECAI 2024)
• Event location: Santiago de Compostela, Spain
• Event website: https://www.ecai2024.eu/
• Event start date: 2024-10-19
• Event end date: 2024-10-24
• DOI: 10.3233/FAIA240894
• EISBN: 9781643685489
• Language: English