In-Network Market Prediction Using Machine Learning and Limit Order Books
2026-08-03 • Networking and Internet Architecture
Networking and Internet ArchitectureComputational Engineering, Finance, and ScienceEmerging Technologies
AI summaryⓘ
The authors explore how to use machine learning directly inside network devices to speed up stock market predictions. They created LOBIN, a system that builds and analyzes limit order books within programmable network switches, cutting down the time it takes to predict price movements compared to traditional servers. Their tests show LOBIN achieves lower latency than standard setups and can process a large part of the trading data without needing servers, with only a small drop in prediction accuracy. Using both switches and servers together further improves the performance.
machine learningalgorithmic tradinglimit order booklatencyprogrammable switchesmarket predictionhigh-frequency tradingnetwork deviceshybrid deploymentinference
Authors
Xinpeng Hong, Changgang Zheng, Joshua Lilley, Stefan Zohren, Noa Zilberman
Abstract
Machine learning is significantly transforming algorithmic trading, yet the requirement for rapid execution speeds persists. While both aspects aim to boost profitability, embedding advanced machine-learning techniques with reduced trading latency presents a notable challenge. Adopting in-network machine learning, which involves offloading inference to programmable network devices, offers a delicate equilibrium in this trade-off. In this paper, we present LOBIN, a solution that utilizes machine learning within the network for market prediction based on high-frequency market data feeds. LOBIN is adept at constructing limit order books and performing inference directly within programmable switches. When compared to server-based benchmarks, LOBIN not only predicts future stock price movements with higher throughput but also maintains robust machine learning performance. It achieves over a 10% reduction in latency compared to the NASDAQ order-matching server benchmark and delivers microsecond-level latency. Furthermore, the machine learning performance of LOBIN can be further enhanced through the adoption of a hybrid deployment approach that integrates both the switch and the servers. Our evaluation demonstrates that among all data feeds of evaluated stocks, the application of hybrid deployment results in approximately 45% of the traffic and 38\% of the total potential transaction value being processed within switches without server intervention, reducing latency while ensuring that the average change in error rate of predictions remains at around 3% relative to benchmarks based solely on server use.