Fools Rush In: Competitive Effects of Reaction Time in Automated Trading

Abstract

We explore the competitive effects of reaction time of automated trading strategies in simulated financial markets containing a single exchange with public limit order book and continuous double auction matching. A large body of research conducted over several decades has been devoted to trading agent design and simulation, but the majority of this work focuses on pricing strategy and does not consider the time taken for these strategies to compute. In real-world financial markets, speed is known to heavily influence the design of automated trading algorithms, with the generally accepted wisdom that faster is better. Here, we introduce increasingly realistic models of trading speed and profile the computation times of a suite of eminent trading algorithms from the literature. Results demonstrate that: (a) trading performance is impacted by speed, but faster is not always better; (b) the Adaptive-Aggressive (AA) algorithm, until recently considered the most dominant trading strategy in the literature, is outperformed by the simplistic Shaver (SHVR) strategy-shave one tick off the current best bid or ask-when relative computation times are accurately simulated.

Agents and Artificial Intelligence

“…This paper extends work by Hanifan and Cartlidge on reaction time of traders, originally published in the 2020 Proceedings of the International Conference on Agents and Artificial Intelligence (ICAART) [19]. Much of the background material presented in Section 2 is reproduced from [19], while Section 3 presents a condensed version of the key results in [19]. Section 4 presents entirely Fig.…”

“…Passive orders that do not cross the spread will rest in the LOB, with position determined by price. (Reproduced from [19]. )…”

“…This section presents a condensed version of an exploration on reaction time of traders, originally published in the 2020 Proceedings of the International Conference on Agents and Artificial Intelligence (ICAART) [19]. For further exploration (including fixed ordering and tournament selection models), we refer the reader to [19] and also Hanifan's MSc thesis [18].…”