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

• DOI: http://doi.org/10.1002/ijfe.1700
• Published date: 01 April 2019
• Date: 01 April 2019

RESEARCH ARTICLE

High‐frequency trading from an evolutionary perspective:

Financial markets as adaptive systems

Viktor Manahov

1

| Robert Hudson

2

| Andrew Urquhart

3

1

The York Management School,

University of York, York, UK

2

Hull University Business School,

University of Hull, Hull, UK

3

Southampton Business School,

University of Southampton, Southampton,

UK

Correspondence

Viktor Manahov, PhD, University of York,

Heslington East, York YO10 5GD, UK.

Email: viktor.manahov@york.ac.uk

JEL Classification: F3; G10; G12; G14;

E47

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 par-

ticipants. To evaluate the evolution of stock price predictability at the millisec-

ond 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.

KEYWORDS

adaptive market hypothesis, efficient market hypothesis, evolutionary computation, genetic

programming, high‐frequency trading, market efficiency

1|INTRODUCTION

Due to the advances in technology and the rapid growth

of high‐frequency trading (HFT), advanced financial mar-

kets have substantially eliminated human intermediation

in the trading process and replaced it with automated

electronic limit order books that have allowed the growth

of trading algorithms as one of the main investment tools.

Some of the trading algorithms generated imitate the

behaviour of humans in the trading process, and over

the last few years, these trading algorithms have substan-

tially improved their speed to match the incidence of bid

and ask orders (McGowan, 2010).

Concerns over financial market stability and the equi-

table treatment of all market participants have prompted

renewed interest in market quality, and market regula-

tors are still debating whether or not HFT is beneficial

or harmful to market efficiency.

1

Because of the seminal

work of Fama (1965, 1970), who introduced the efficient

market hypothesis (EMH), there has been a plethora of

studies analysing market efficiency and adaptability.

Recently, this topic has been brought into new focus by

the rapid growth of profitable HFT (Baron, Brogaard, &

1

Whereas Zhang (2010), Kirilenko, Kyle, Samadi, and Tuzun (2011),

Biais, Foucalt, and Moinas (2013), Foucault, Hombert, and Rosu

(2013) show that HFT can have harmful effects on market quality,

Domowitz (2010), Brogaard, Hendershott, and Riordan (2014),

Boehmer, Fong, and Wu (2012), Jovanovic and Menkveld (2012) Marti-

nez and Rosu (2013) Carrion (2013), Hansbrouck and Saar (2013) argue

that HFT play a positive role on market quality.

Received: 20 April 2017 Revised: 30 July 2018 Accepted: 10 September 2018

DOI: 10.1002/ijfe.1700

Int J Fin Econ. 2019;24:943–962. © 2018 John Wiley & Sons, Ltd.wileyonlinelibrary.com/journal/ijfe 943

Kirilenko, 2012). However, many studies of market effi-

ciency have significant deficiencies such as data‐snooping

(Sullivan, Timmermann, & White, 1999), ex‐post selec-

tion of profitable trading rules (Zakamulin, 2014), false

discoveries (Harvey & Lui, 2014), inattention to transac-

tion costs (Park and Irwin (2007), as well as studies

basing their conclusions on econometric tests or theoret-

ical hypotheses that treat market properties as essentially

static, failing to consider the evolutionary processes of

adaptation, learning, and survival of market participants

(Campbell, Lo, & MacKinlay, 1997). Lo (2004) argues that

market outcomes are obtained not in an analytical way

but through an evolutionary process of trial‐and‐error

and natural selection. The process of natural selection

enables survival of the fittest and determines the compo-

sition of market participants and their trading strategies.

In contrast, this study implements a special adaptive form

of the strongly typed genetic programming (STGP) utiliz-

ing historical millisecond data of the most capitalized

companies: Apple, Exxon Mobil, and Google. The STGP

(described in Appendix A) represents a sophisticated trad-

ing algorithm that successfully replicates real‐life trading

strategies performed at the millisecond time frame. Using

STGP, we compare the forecasting performance of our

artificial traders with several combined forecasting

methods. In other words, we simulate real‐life trading

sessions that allow us to avoid the obstacles in the studies

discussed above. Given the arguments of Lo (2004, 2005)

that financial markets are governed by evolutionary

processes, STGP is an extremely suitable approach to

investigate market efficiency. This is due to the fact that

all 100,000 artificial traders in each of the three stock

markets in our experiment compete, learn, adapt, evolve,

and try to survive. The environment of heterogeneous

traders where stock prices and traders' beliefs co‐evolve

over time provides an appropriate laboratory platform to

investigate market efficiency. Hommes (2011) suggests

that adaptation and learning in heterogeneous structures

are important tools for analysis of financial market

behaviour. Moreover, the random nature of the initial

trading rules of all traders and their subsequent evolution

allows us to observe directly the processes described by

Lo (2004, 2005). Therefore, the aim of this study is to

evaluate the evolution of stock price predictability at the

millisecond time frame and to examine whether this evo-

lution is consistent with the notion of adaptive markets.

The contribution of this study is three fold. First, this

is the first study to use an innovative trading algorithm

and real‐life millisecond data to provide concrete empiri-

cal evidence of market adaptability at the millisecond

time frame. We estimate in precise quantitative terms

the daily profits of HFTs after taking into account realis-

tic transaction costs, providing an advantage over existent

studies, such as that of Brogaard (2013) and Carrion

(2013), which observed the activities of HFT using only

aggregate data, thus preventing them from calculating

the exact profitability. In order to measure the statistical

accuracy and trading efficiency, we compare the predic-

tive ability of our artificial traders with benchmarks of

forecast combination approaches such as the support vec-

tor regression (SVR), the least absolute shrinkage and

selection operator (LASSO), and the Kalman filter (KF).

Second, we take into account all the issues in previous

studies as potentially affecting the reliability of trading

results. The presence of 100,000 artificial traders in our

experiment ensures forecasting model stability and lower

sensitivity to random factors. All artificial traders learn

from their experience, evaluating the profitability of

trading rules based on their predictive power rather than

in‐sample fit. We also avoid data‐snooping biases by

ensuring all trading rules are evaluated and executed by

artificial traders.

Third, we observe that various heuristics enable artifi-

cial traders to be ecologically rational, making adaptive

decisions that combine forecasting accuracy with speed.

We have found that market participants learn, compete,

adapt, survive, and evolve towards a higher degree of

sophistication. These findings suggest that our artificial

stock markets can be modelled as evolving ecological

systems that consist of large numbers of heterogeneous

traders competing for profits on each market. Such

ecological systems experience not only varying degrees

of efficiency but also cycles of efficiency and adaptability

as changes in profit opportunities lead to shifts in the

composition of market participants. Therefore, we find

strong evidence to show that market participants can be

modelled in a way supportive of the adaptive market

hypothesis (AMH).

The remainder of this paper is organized in the fol-

lowing way: Section 2 comprises the literature review,

whereas Section 3 presents the experimental design of

the three artificial stock markets, the forecasting models,

and data utilized in this study. Section 4 reports the

artificial agents' trading activity and profitability, whereas

Section 5 presents the conclusions. Additional clarifying

and technical material can be found in Appendix A.

2|LITERATURE REVIEW

2.1 |The adaptive market hypothesis

The AMH, formulated by Andrew Lo (2004, 2005), argues

that many of the behavioural biases in finance are in fact

consistent with an evolutionary model of investors learn-

ing and adapting to a changing environment. It is the

impact of these evolutionary forces on financial

944 MANAHOV ET AL.