Intelligent trading architecture

Abstract

SummaryThis work presents the Intelligent Trading Architecture (ITA), which is a new automated trading system architecture that supports multiple strategies for multiple market conditions through hierarchical trading signals generation. The central idea of the proposed system architecture is decomposing the trading problem into a set of tasks that are handled by distributed autonomous agents under a minimal central coordination. With this kind of architecture, we can take advantage of currently available and future high‐performance computing systems. These systems, due to the way computer architecture has evolved in the recent past and foreseeable future, are composed of multiple processor cores. We are implementing the ITA software architecture employing the Carnegie Mellon Navigation (CARMEN) robot control software and using a publish/subscribe communication model. Together, CARMEN and this communication model allow the implementation of high‐performance, scalable parallel computing systems that leverage the architecture of multi‐core systems. For this work, we evaluated the data structures and algorithms employed by the symbol module of the ITA software architecture, which is responsible for maintaining the synchronized local copies of exchanges limit order books (LOB) for the instruments traded by the system. Our LOB implementation strongly outperformed a reference implementation in all evaluated parameters by more than one order of magnitude in some cases, achieving average throughputs of 4 million orders/s when creating new orders, 3 million orders/s when changing existing orders, and 17 million orders/s when querying orders. Copyright © 2015 John Wiley & Sons, Ltd.