Algo Trading Presentation PDF

Download as pdf or txt
Download as pdf or txt
You are on page 1of 18
At a glance
Powered by AI
The key takeaways are that algorithmic trading and electronic foreign exchange trading are growing significantly due to decreasing technology barriers and costs, growing market access, and the ability to make profits. Algorithmic trading is being adopted by various types of financial institutions and traders.

Algorithmic trading is exploding because technology barriers are decreasing in cost, market access is growing through electronic communication networks which allow for anonymity and order placement. Technological growth on the buy and sell-side through APIs and ability to process thousands of orders at low cost. Significant profits can be made through algorithmic trading.

Some applications of algorithmic trading include trading signal automation, auto-hedging to maximize profits and reduce risks, risk allocation algorithms to automatically adjust exposures, market making through intelligent pricing, and execution engines to optimize order routing and discover liquidity.

Algorithmic Presentation to

European Central Bank


Jean-Marc Orlando, EFX Global Head BNP PARIBAS
What’s all the BUZZ about Algorithmic Trading /eFX ?

1
Why is Algorithmic Trading Exploding in the industry?

Its Growing because Target Clientele

„ Technology Barrier is less „ Hedge Funds


expensive
„ CTA’s
„ As market access grows via
ECN’s anonymity and „ Proprietary Trading Houses
powerful ability to place orders „ Bank Proprietary Trading
are are more easily achieved Desks
(Prime Brokerage and Market
Access(EBS, Reuters) „ Corporates

„ Technological Growth on Buy/ „ Retail


Sell Side (API’s, processing „ Next generation market
thousands of tickets at minimal makers
cost.
„ Euros are being made!!!!

2
Average Reported Buy-Side Trading Volume by Geography

2006 2005

„ Global $70.6T 59.0


„ Europe $42.3T 35.9
„ Americas $20.5T 16.8
„ Asia Pacific $ 7.4T 6.1
„ Asia (ex Japan) $ 5.2T 3.6
„ Japan $ 1.7T 2.2

Based on Interviews with 1,663 institutions in 2006 and 1,549 in 2005.


Greenwich Associates

3
Adoption of FX Electronic Trading Globally

2006 2005

„ Trade Online 53% 44%


„ Plan to Start 11% 13%
„ Not Considering 36% 43%

2006 Total Reported Electronic Volume = $35.5 Trillion


2005 Total Reported Electronic Volume = $16.9 Trillion
Greenwich Associates

4
Current and Expected FX e-Trading Activity Globally

Current % of Volume 2006 2005 2004


„ Electronic 60% 53% 48%

„ Traditional 40% 47% 52%

Expected % of Volume 2006 2005 2004


„ Electronic 63% 57% 54%

„ Traditional 37% 43% 46%

Based on responses from 628 instituitions trading electronically in 2004, 679 in 2005, 877 in 2006
Greenwich Associates

5
Algo & e-FX proliferate growth in the search for Alpha

$2.5 Trillion Traded Daily from $1 Trillion


Based on research conducted by Client Knowledge 2007 and CK estimate based on recent Fed and BoE data

6
How are algo trading revenues split today?

Algorithmic Execution (The art of microstructure trading)

ƒ VWAP, TWAP, Time Slicing, icebergs, etc (order routing)


ƒ Orders – utilization of client intelligence
ƒ High Frequency and Provides Information
ƒ Is becoming a source of low margin revenue, radical shift of
strategy in financial institutions offering

Algorithmic Trading (Replacing traditional manpower )

ƒ Electronic market Making


ƒ Auto Hedging
Proprietary Trading
ƒ If I told you I would have to kill you…

7
Algo is the vehicle, Market Data the Fuel but what is the cost?

Cost Variables:
Market Data STP Protocols
Real Time Data Compliance
Historical Data MiFID
Connectivity APIs
Infrastructure / Network Algo Maintenance
Latency Tools Algo Creation (Quants)
ECN brokerage IT specialists
E-sales Client Analysis
Back Office Marketing
Security Ticket Processing
Prime Brokerage Order System etc…

=
??
What you do know is that the future of
your business is at risk if you don’t
do it….
8
Using Algorithms to Increase Business

„ The Classic approach:


¾Traditional traders claim to master the feel / instincts to
make money
¾Trading behavior can be analyzed using a systematic
approach
¾This exercise leads to a list of conditional rules which
can result in a extremely complex decision tree
¾Traders process a wide panacea of market information
that is aggregated by the brain producing a trading
decision:
‰ Visual information (prices, graphs, news, flows) coming from various
economical sources
‰ Audible information (news, market noises, internal / external flow trading)
‰ Accumulated information that form a market sentiment (a feeling)

¾ Everythingthat can be formulated is a candidate for


algorithmic trading

9
Using Algorithms to Increase Business

„ The Approach going forward:


¾Algorithmic rule-based approach enables:
‰ Reproduction , enhancement (speed, accuracy) and trading behaviors
‰ Creation of new trading paradigms by overcoming brain calculation limitations (the
brain used to be a winner because of its unique synthetic approach; chess has
been for long a battle ground but debate is over)

¾The challenge is to program computers with complex


rules and awareness of corner cases which humans
have no problem recognizing.
¾The traditional first level algorithmic application reveals
weakness as humans typically outperform simple and
linear problems.
¾Algorithmic trading requires sophisticated quantitative
methodologies and techniques.

10
Unlocking Artificial Intelligence
„ Since mid 20th century, researchers have heavily contributed in the
development artificial intelligence.
„ Much like neural organization, it is not about the complexity of the basic
constituents but more about the complexity of their assembly
„ Most Algorithmic topics focus on simple inference engines that link
ensembles with decision trees resembling a living intelligent design.
„ The backbone of Algorithmic is machine learning which is an extension
of statistical science. Most of you have already dealt with this concept
by implementing a simple regression calculation!!!
„ Today’s Algorithmic trading is involves neural networks, fuzzy logic,
pattern recognition…
„ Make no mistake, there is no magic or wizardry.. It is always a more
evolved form of regression technique using more/less complex filter
design…
„ Again, complexity is more in the circumvolution of these algorithms.

11
Algo – Magic or Science ??

12
Algo Trading Strategies

¾ SignalProcessing: Mathematical extension of technical analysis based
on the art of filtering to eliminate noise and discern trading patterns

¾ Market Sentiment: The computer is entirely unaware of market activity


until you feed a model market data flows. The algorithm becomes aware
of market agitation and participant activity. The intent is to provide algos
the appropriate context to analyze and learn market psychology of
supply and demand.
¾ News Reader: Algos are not reacting to major political events unless
you teach them how to artificially read news headlines

¾ Pattern
Recognition: Enable the machine to learn, adapt and re-act
when patterns arise creating revenue opportunities.
• Note: Single strategies are vulnerable: It is in the mix and diversification that algos
show strengths and consistent productivity

13
Trading Strategies

14
Algo Trading Applications

„ Trading Signals Automate: Design proprietary strategies to generate


non-traditional revenue pools with cold steel and logical trading
behaviors
„ Auto Hedging: Manage trade flows to maximize revenues/ reduce risk
in a high frequency mode..
„ Risk Allocation Algorithm: Automatically adjust your portfolio
exposures to adapt to the current market conditions optimizing revenues
„ Pricing: Market making generation via intelligent auto-pricing that
adapts to market volatility, current position and activities of market
participants. Ability to answer thousands of price requests accurately
and in rapid succession, enabling new market standard adjustments.
„ Execution Engines: Enable programs to search/discover fragmented
liquidity pools to optimize execution via complex / high frequency order
routing strategies

15
Cycle of Algo trading
1. Idea derivation is predominantly based on market intuition and practice
2. Discover quantitative support to model initial instincts. Surprisingly this
discovery comes from very diverse industries & scientific fields
3. Sketch & Prototype research algorithms
4. Backtest and evaluate robustness and productivity
5. Improve production via cross fertilization of existing algorithmic library
6. Test algorithms in semi-vivo environment to detect corner cases and
validate in/out sample results
7. Design and implement production version
8. Monitor real time signals: Algorithmic baby-sitting
9. Refine models constantly with live observation/adjustments.
10. Recycle technology to other asset classes and diversify frequency and
candidates

16
Dangers related to Algo Trading
„ No human intervention: need to hunt for corner cases as programs
have no conscience of improper trading activities. Time is spent in
design regarding: security, limits breaches, controls, etc…
„ IT becomes an unprecedented dependency (servers, networks,
hardware, data feeds, latencies)
„ Your success relies on a100% error-free code (memory leakage,
infinite loops.etc). The risk of running a bugged algorithm can be
enormous especially if in-vivo at high frequency.
„ Uptime monitoring requirements have to be high and attending
resources must be highly educated
„ The technology is highly portable and risks of information property
infringement are high by nature
„ Market volatility lowers by wide spreading of algorithmic activity and
chances of contagious systemic collapses are increased
„ No universal recipe and promotion of human risk managers to
activate/deactivate automates (mean reversion, trends)
„ As in the Aviation industry, even if auto-pilots are capable of landing
airplanes smoother then human pilots, the need for experienced
supervisors is required in case of a major systemic failure (9/11).
17

You might also like