Ernest Chan - szkolenie z ALGORITHMIC TRADINGU

[europrop.poland]

Zapraszamy na szkolenie z algorithmic tradingu, które będzie prowadzone przez jednego z czołowych autorytetów w tej dziedzienie - Ernesta Chana.
Szkolenie rozpocznie się 22 października i będzie prowadzone ONLINE przez 2 tygodnie ( ok. 2-3 godziny dziennie).

Zgłoszenia prosimy kierować na: poznan@europroptrading.com

Cena: 1950 zł + VAT

Informacje na temat szkolenia:

Backtesting & Optimization

This training program is designed for traders, risk managers, system developers, hedge funds and investment managers, aspiring to learn how to accurately test trading strategies on short term scales. This course gives the trainee a technical, fundamental and practical understanding for effective back-testing, optimization, and risk control.

Key to developing a successful trading system is the ability to take a good idea, accurately back test, and optimize the strategy. Yet the process is not as simple or carefree as it may appear on the surface. Being able to access reliable data is one matter but there are a host of other concerns that system developers need to be aware of. Dr. Chan elucidates these issues and provides a methodical approach to testing and optimization.

Choosing a backtest platform
+ Criteria for choosing a suitable backtest platform
+ Discussion of pros and cons of each platform
+ Special considerations for backtesting high frequency strategies
+ Why do we choose MATLAB?
Choosing a historical database
+ Criteria for choosing a good historical database
+ Discussion of pros and cons of each database

The Essentials of MATLAB
+ Quick survey of syntax
+ Building some useful utilities for trading and plotting simple graphs
+ Using toolboxes
Exercise: backtesting various types of strategies
+ Single ETF/stock/currency
+ Futures: Handling rollovers and backtesting seasonal strategies
+ Portfolio of stocks

Performance measurement
+ Returns and excess returns
+ Drawdown calculation
+ The importance of Sharpe ratio
+ Subtleties in Sharpe ratio calculation
Ways in which your backtest may not reflect reality
+ Look-ahead bias
+ Data-snooping bias and ways to avoid it
+ Survivorship bias
+ Impact of noisy data on different types of strategies
+ Impact of historical or current short-sale constraint
+ Impact of transaction costs
+ Volume constraint
+ Regime change
+ The importance of paper trading

Optimisation of parameters
+ Using MATLAB to optimize
+ Using Alphacet Discovery to optimize (Demo)
+ Interpolating the optimal parameters
+ Pitfalls of parameter optimization
+ What is "portfolio optimization" and do you need it?
Money and risk management
+ Optimal capital allocation and leverage via "correlation analysis" and the Kelly formula for continuous finance

[reptile]

To mi wyglada na seminarium mini QA .. raczej statystyke backtesting a nie Algo trading.. zrobienie analiz to jedno a urzeczywistnienie systemu do live to chyba 90% czego tutaj nie ma ?A cena? Hmm

[europrop.poland]

Szkolenie zostaje dodatkowo wzbogacone o Statistical Arbitrage. Szczegółowy program szkolenia znajduje się poniżej:

BACKTESTING & OPTIMIZATION
OVERVIEW
• What is backtesting and how does it differ from “simulations” ?
• Why is backtesting a necessary step for profitable automated trading ?
• Why is backtesting not a sufficient step to ensure profitability in automated trading ?
• What can we do to increase the predictive power of our backtest results
• Incorporating optimization and money/risk management schemes in your backtest.
• How to identify good/bad strategies even before a backtest.
CHOOSING A BACKTEST PLATFORM
• Criteria for choosing a suitable backtest platform. + A list of backtesting platforms.
• Discussion of pros and cons of each platform.
• Special note: backtesting high frequency strategies.
• Why do we choose MATLAB?
CHOOSING A HISTORICAL DATABASE
• Criteria for choosing a good historical database.
• Biases in historical databases.
• Discussion of databases for different asset classes.
TUTORIAL TO MATLAB
• Quick survey of syntax.
• Exercises: building some utilities useful for trading and plotting simple graphs.
• Using toolboxes:
• Datafeed toolbox.
• Statistics toolbox.
• Financial, financial derivatives, fixed-income, econometrics, optimization, neural
network, wavelet toolboxes. + Freeware: Spatial-econometrics.com
BACKTESTING & OPTIMIZATION
PERFORMANCE MEASUREMENT
• Returns and excess returns.
• Drawdown calculation.
• The importance of Sharpe ratio.
• Subtleties in Sharpe ratio calculation.
• Transaction costs estimation.
WAYS IN WHICH YOUR BACKTEST MAY NOT REFLECT REALITY
• Look-ahead bias.
• Data-snooping bias and ways to avoid it
• Out-of-sample testing and why it is not a panacea. + Cross validation
• Randomization
• Survivorship bias.
• Impact of noisy data on different types of strategies.
• Impact of historical or current short-sale constraint.
• Impact of transaction costs.
• Volume constraint.
• Regime change.
• The importance of paper trading
OPTIMIZATION OF PARAMETERS
• Using MATLAB to optimize.
• Interpolating the optimal parameters.
• Pitfalls of parameter optimization.
• What is “portfolio optimization” and whether you really need it.
MONEY AND RISK MANAGEMENT
• Risk management and optimal capital allocation and leverage via “correlation analysis” and
the Kelly formula for continuous finance.
This training program introduces students to using statistical arbitrage strategies with particular
reference to research, testing and implementation. Students learn how to apply statistical
arbitrage to a variety of trading styles, including pairs and triplets trading, momentum, index
arbitrage, and long-short portfolios. Relevant software (MATLAB) is used throughout the course to
illustrate examples and to help students practice the essential steps in developing a statistical
arbitrage strategy.
No programming skills required

STATISTICAL ARBITRAGE
OVERVIEW
• Types of statistical arbitrage strategies: directional trading, pairs and other cointegrated portfolio
trading, index arbitrage, long-short portfolio, momentum and factor models.
• Stationarity, cointegration, mean reversion, and momentum.
TUTORIAL TO MATLAB
• Why is MATLAB superior to Excel/VBA/Java/C++/C# for statistical arbitrage research?.
• Overview of capabilities as research and backtesting platform.
• The pros and cons of using MATLAB as automated trading platform.
• Quick survey of syntax.
• Exercises: building some utilities useful for trading research.
DIRECTIONAL TRADING
• Concept of stationarity, and why it is useful.
• Statistical test for stationarity: adf.
• Exercise: Using MATLAB and spatial-econometrics toolbox to find out if AUDCAD and EURCHF
is stationary.
• Test for mean-reversion: computing half-life based on Ornstein-Uhlenbeck formula.
• Why is computing half-life better than computing average holding period?
• Exercise: Compute the half-life of mean-reversion for AUDCAD.
• Exercise: Backtest a Bollinger-band strategy for AUDCAD and EURCHF.
STATISTICAL ARBITRAGE
PAIRS AND TRIPLET TRADING
• Concept of cointegration, and why is it useful.
• How is cointegration different from correlation?
• Statistical tests for cointegration: cadf and Johansen.
• Exercise: Find out if GLD-GDX is cointegrating.
• Finding the best hedge ratio.
• Exercise: Backtest a Bollinger-band strategy on GLD-GDX and other pairs.
• Trading cointegrated triplets.
• Exercise: Backtest a Bollinger-band strategy on GLD-GDX-USO.
• What are the best markets to pair-trade?
INDEX ARBITRAGE
• Trading an ETF against a basket of its component stocks.
• Two ways of constructing a basket.
• Exercise: Backtest a trading model of XLE against its components.
LONG SHORT PORTFOLIO
• Ranking stocks in an index based on various simple returns criteria.
• How minor variations in strategies can produce big differences in returns.
• Important biases and pitfalls in backtesting long-short portfolio strategies.
• Exercise: Backtest variations of a long-short portfolio strategy.
MOMENTUM STRATEGIES AND FACTOR MODELS
• Types of event-driven momentum: PEAD, merger arbitrage, etc.