Download High Frequency Trading PDF

TitleHigh Frequency Trading
File Size2.8 MB
Total Pages257
Table of Contents
                            About the Editors
About the Authors
Preface
The Volume Clock: Insights into the High-Frequency Paradigm
Execution Strategies in Equity Markets
Execution Strategies in Fixed Income Markets
High-Frequency Trading in FX Markets
Machine Learning for Market Microstructure and High-Frequency Trading
A “Big Data” Study of Microstructural Volatility in Futures Markets
Liquidity and Toxicity Contagion
Do Algorithmic Executions Leak Information?
Implementation Shortfall with Transitory Price Effects
The Regulatory Challenge of High-Frequency Markets
Index
                        
Document Text Contents
Page 1

High-Frequency

EditEd By david EaslEy,
Marcos lópEz dE prado,
and MaurEEn o’Hara

trading
New Realities for Traders,
Markets and Regulators

H
igh-Frequency trading

Edited By d
avid Easley, M

arcos lópez de prado, and M
aureen o

’H
ara

Praise for the book:

“High Frequency Trading offers a much-needed collection of complementary
perspectives on this hottest of topics. The combined academic credentials and
first-hand market knowledge of the editors is probably unparalleled, and their
style of writing precise and engaging. The book is thoughtfully organized, tightly
focussed in its coverage and comprehensive in its scope. Practitioners, academics
and regulators will greatly benefit from this work.”
RiccaRdo RebonaTo, Global Head of Rates and FX analytics, PiMco,
and Visiting Lecturer, University of oxford.

“This book is a must read for anyone with any interest in high frequency trading.
The authors of this book are a who’s who of thought leaders and academics
who literally did the fundamental research in the innovation, development,
and oversight of modern electronic trading mechanics and strategies.”
LaRRy Tabb, Founder & ceo, Tabb Group, and Member of the cFTc
Subcommittee on automated and High Frequency Trading.

“The concept of high frequency trading too often evinces irrational fears
and opposition.  This book, by experts in the field, unveils the mysteries,
records the facts and sets out the real pros and cons of such mechanisms.”
cHaRLeS GoodHaRT, Fellow of the british academy, and emeritus Professor
at the London School of economics.

“Easley, Lopez de Prado, and O’Hara have produced a classic that everyone
should have on their shelves.”
aTTiLio MeUcci, chief Risk officer at KKR, and Founder of SyMMyS.

PEFC Certified

this book has been
produced entirely from
sustainable papers that
are accredited as pEFc
compliant.

www.pefc.org

High Frequency Trading V2.indd 1 09/10/2013 16:34

Page 2





“Easley” — 2013/10/8 — 11:31 — page i — #1












High-Frequency Trading

Page 128





“Easley” — 2013/10/8 — 11:31 — page 107 — #127












MACHINE LEARNING FOR MARKET MICROSTRUCTURE AND HIGH-FREQUENCY TRADING

Figure 5.4 Correlations between feature values and learned policies

1 2
3 4

5 6

0

5

10

15

20

–0.10

0

0.10

0.20

Fea
ture

ind
ex

Policy index

C
o
rr

e
la

tio
n
w

ith
a

ct
io

n
(+

1
=

b
u
y,


1
=

s
e
ll)

For each of the six features and nineteen policies, we project the policy onto
just the single feature compute the correlation between the feature value and
action learned (+1 for buying, −1 for selling). Feature indexes are in the order
bid–ask spread, price, smart price, trade sign, bid–ask volume imbalance, signed
transaction volume.

payout for both actions across all visits to x in the train-
ing period was computed. Learning then resulted in a pol-
icy, π , mapping states to action, where π(x) is defined to be
whichever action yielded the greatest training set profitability
in state x.

4. Testing of the learned policy for each name was performed
using all 2009 data. For each test set visit to state x, we took the
action π(x) prescribed by the learned policy, and computed
the overall 2009 profitability of this policy.

Perhaps the two most important findings of this study are that
learning consistently produces policies that are profitable on the test
set, and that (as in the optimised execution study), those policies
are broadly similar across stocks. Regarding the first finding, for all
19 names the test set profitability of learning was positive. Regard-
ing the second finding, while visualisation of the learned policies
over a six-dimensional state space is not feasible, we can project the
policies onto each individual feature and ask what the relationship
is between the feature and the action learned. In Figure 5.4, for each

107

Page 129





“Easley” — 2013/10/8 — 11:31 — page 108 — #128












HIGH-FREQUENCY TRADING

Figure 5.5 Comparison of test set profitability across 19 names for
learning with all six features (black bars, identical in each subplot)
versus learning with only a single feature (grey bars).

–500

0

500

1000

1500

2000

2500

3000

0 5 10 15 20

(a)

–500

0

500

1000

1500

2000

2500

3000

0 5 10 15 20

(b)

–2000

–1000

0

1000

2000

3000

0 5 10 15 20

(c)

(a) Spread versus all. (b) Price versus all. (c) Smartprice versus all.

108

Page 256





“Easley” — 2013/10/8 — 11:31 — page 235 — #255












INDEX

and predicting price
movement from order
book state, 92–3

and price movement from
order book state,
predicting, 104–15

and reinforcement learning
for optimised trade
execution, 96–104

and smart order routing in
dark pools, 115–22

market stress:
and central bank

interventions, 79–80
and flash crash (2010), 77–8;

see also flash crash
and yen appreciation (2007),

77
and yen appreciation (2011),

78–9
Markets in Financial

Instruments Directive
(MiFID), 2, 21, 143, 216

microstructural volatility:
in futures markets, 125–41,

133, 134, 136, 137, 138–9
experimental evaluation,

133–40
HDF5 file format, 127
maximum intermediate

return, 131–2
parallelisation, 132–3
test data, 126–7
and volume-synchronised

probability of informed
trading, 128–31

MIDAS, see Market Information
Data Analytics System

N

Nasdaq, CME’s joint project
with, xvi

O

optimised trade execution,
reinforcement learning for,
96–104

order book imbalance, 36–8

order-flow toxicity contagion
model, 146–51

see also liquidity and toxicity
contagion

order protection and fair value,
38–41, 40

P

pack hunters, 9
parallelisation, 132–3
price movement from order

book state, predicting,
104–15

pro rata matching, 44, 59–62
probability of informed trading

(PIN), 7
Project Hiberni, xvi

Q

quote danglers, 9
quote stuffers, 9

R

regulation and high-frequency
markets, 81, 207–9, 210,
212, 214

good and bad news
concerning, 208–14

solutions, 214–28
and greater surveillance and

coordination, proposals
for, 215–18

and market rules, proposals
to change, 218–25

and proposals to curtail
HFT, 225–8

Regulation National Market
System (Reg NMS), 2, 21,
143, 219

Regulation SCI, 216
reinforcement learning for

optimised trade execution,
96–104

Rothschild, Nathan Mayer, 1

S

smart order routing in dark
pools, 115–22

spread/price–time priority, 82–3

235

Page 257





“Easley” — 2013/10/8 — 11:31 — page 236 — #256












HIGH-FREQUENCY TRADING

T

time, meaning of, and
high-frequency trading,
5–7, 7

Tobin tax, 17, 81, 87
Tradeworx, 215
trading algorithms, 69–72

and algorithmic
decision-making, 71–2

and algorithmic execution,
70–1

evolution of, 22–8
generations, 23–7
and indicator zoology, 27–8

see also algorithms
trading frequencies, in currency

market, 65–73, 72, 73; see
also foreign-exchange
markets

trading signals:
construction of, 31–8

and order book imbalance,
36–8

and timescales and weights,
31–3, 33

and trade sign
autocorrelations, 34–6

transaction cost, and algorithms,
28–31

transitory price effects:
approach to, illustrated,

192–203
daily estimation, 195–9
implementation shortfall

calculations, 193–5

intra-day estimation,
199–203

and information shortfall,
185–206, 196, 197, 198, 199,
200, 202, 203

discussed, 186–9
implementation details,

204–5
and observed and efficient

prices and pricing errors,
189–92

Treasury futures, 46, 47, 48, 51,
52, 55

V

volume clock, 1–17, 7
and time, meaning of, 5–7

volume-synchronised
probability of informed
trading, 128–31

bars, 128
buckets, 129–30
cumulative distribution

function, 130–1
volume classification, 128–9

W

Walter, Elisse, 216
Waterloo, Battle of, 1

Y

yen appreciation:
2007, 77
2011, 78–9
see also market stress

236

Similer Documents