High‐frequency trading from an evolutionary perspective: Financial markets as adaptive systems

Abstract

The recent rapid growth of algorithmic high‐frequency trading strategies makes it a very interesting time to revisit the long‐standing debates about the efficiency of stock prices and the best way to model the actions of market participants. To evaluate the evolution of stock price predictability at the millisecond timeframe and to examine whether it is consistent with the newly formed adaptive market hypothesis, we develop three artificial stock markets using a strongly typed genetic programming (STGP) trading algorithm. We simulate real‐life trading by applying STGP to millisecond data of the three highest capitalized stocks: Apple, Exxon Mobil, and Google and observe that profit opportunities at the millisecond time frame are better modelled through an evolutionary process involving natural selection, adaptation, learning, and dynamic evolution than by using conventional analytical techniques. We use combinations of forecasting techniques as benchmarks to demonstrate that different heuristics enable artificial traders to be ecologically rational, making adaptive decisions that combine forecasting accuracy with speed.

The adaptive market hypothesis and high frequency trading

“…We suspect that accessing message level market data is the primary obstacle. Those that do make the connection include: Virgilio, which finds that HFT allows a few fast traders to profit from arbitrage and thus falsifies the EMH [ 43 ]; Manahov and Hudson, which uses simulation to demonstrate that a larger market with more heterogenous traders is the key to increased efficiency [ 3 ]; and Manahov, et al ., which concludes that heuristics enable artificial traders to adapt to changing market environments [ 7 ]. Recently, research on the AMH in nascent cryptocurrency markets has become popular.…”

“…These papers—Chu, et al . and Manahov, et al .—agree that studying HFT and the AMH properly requires greater granularity in the data, something not always readily available [ 7 , 44 ]. We benefit from having access to message level exchange data, and this enables us to make an empirical contribution that connects HFT to the AMH on a meaningful timescale.…”

“…This supports the argument that HFTs seek to profit and reduce risk by removing short-term inefficiencies [ 6 ]. Thus, HFTs appear to adapt quickly to the evolving level of market efficiency as a means of survival, as suggested by some scholars [ 7 , 8 ]. In our review, this paper is the first to document the relationship between the level of support for the EMH and the level of HFT activity.…”

Online feedback and crowdfunding finance in China

“…The development of the entrepreneurial sector has remained an essential driver of economic growth in the past. However, digitalization has transformed the scope of challenges faced by entrepreneurs, as well as the behaviour of investors (Alexiou, Vogiazas, & Nellis, 2018; Manahov, Hudson, & Urquhart, 2018). It has significantly changed the ways of funding start‐ups and alternative sources of finance available to the entrepreneurs.…”

Evaluating active investing with generic trading reactions

“…Gao, Han, Li, & Zhou, 2018; Marshall et al, 2008). Using a strongly typed genetic programming trading algorithm applied in artificial stock markets, Manahov (2016) and Manahov, Hudson, and Urquhart (2019) investigate stock price predictability at a millisecond time frame. The results indicate profit opportunities whose evolutionary pattern support the adaptive market hypothesis as described in Lo (2004).…”