Successful Algorithmic Trading

I Introducing Algorithmic Trading
Introduction to the Book
Introduction to QuantStart
What is this Book?
Who is this Book For?
What are the Prerequisites?
Software Installation
Installing Python
Obtaining Financial Data
Book Structure
What the Book does not Cover
Where to Get Help
What Is Algorithmic Trading?
Overview
Advantages
Disadvantages
Scientific Method
Why Python?
Can Retail Traders Still Compete?
Trading Advantages
Risk Management
Investor Relations
Technology
II Trading Systems
Successful Backtesting
Why Backtest Strategies?
Key Reasons to Backtest Strategies
Backtesting Biases
Optimisation Bias
Look-Ahead Bias
Survivorship Bias
Cognitive Bias
Exchange Issues
Order Types
Price Consolidation
Forex Trading and ECNs
Shorting Constraints
Transaction Costs
Commission
Slippage
Market Impact
Backtesting vs Reality
Automated Execution
Backtesting Platforms
Programming
Research Tools
Event-Driven Backtesting
Latency
Language Choices
Integrated Development Environments
Colocation
Home Desktop
VPS
Exchange
Sourcing Strategy Ideas
Identifying Your Own Personal Preferences for Trading
Sourcing Algorithmic Trading Ideas
Textbooks
The Internet
Journal Literature
Independent Research
Evaluating Trading Strategies
Obtaining Historical Data
III Data Platform Development
Financial Data Storage
Securities Master Databases
Financial Datasets
Storage Formats
Flat-File Storage
Document Stores/NoSQL
Relational Database Management Systems
Historical Data Structure
Data Accuracy Evaluation
Automation
Data Availability
MySQL for Securities Masters
Installing MySQL
Configuring MySQL
Schema Design for EOD Equities
Connecting to the Database
Using an Object-Relational Mapper
Retrieving Data from the Securities Master
Processing Financial Data
Market and Instrument Classification
Markets
Instruments
Fundamental Data
Unstructured Data
Frequency of Data
Weekly and Monthly Data
Daily Data
Intraday Bars
Tick and Order Book Data
Sources of Data
Free Sources
Commercial Sources
Obtaining Data
Datareader and Pandas
DTN IQFeed
Cleaning Financial Data
Data Quality
Continuous Futures Contracts
IV Modelling
Statistical Learning
What is Statistical Learning?
Prediction and Inference
Parametric and Non-Parametric Models
Supervised and Unsupervised Learning
Techniques
Regression
Classification
Time Series Models
Time Series Analysis
Testing for Mean Reversion
Augmented Dickey-Fuller Test
Testing for Stationarity
Hurst Exponent
Cointegration
Cointegrated Augmented Dickey-Fuller Test
Why Statistical Testing?
Forecasting
Measuring Forecasting Accuracy
Hit Rate
Confusion Matrix
Factor Choice
Lagged Price Factors and Volume
External Factors
Classification Models
Logistic Regression
Discriminant Analysis
Support Vector Machines
Decision Trees and Random Forests
Principal Components Analysis
Which Forecaster?
Forecasting Stock Index Movement
Python Implementations
Results
V Performance and Risk Management
Performance Measurement
Trade Analysis
Summary Statistics
Strategy and Portfolio Analysis
Returns Analysis
Risk/Reward Analysis
Drawdown Analysis
Risk and Money Management
Sources of Risk
Strategy Risk
Portfolio Risk
Counterparty Risk
Operational Risk
Money Management
Kelly Criterion
Risk Management
Value-at-Risk
Advantages and Disadvantages
VI Automated Trading
Event-Driven Trading Engine Implementation
Event-Driven Software
Why An Event-Driven Backtester?
Component Objects
Events
Data Handler
Strategy
Portfolio
Execution Handler
Backtest
Event-Driven Execution
Trading Strategy Implementation
Moving Average Crossover Strategy
S&P500 Forecasting Trade
Mean-Reverting Equity Pairs Trade
Plotting Performance
Strategy Optimisation
Parameter Optimisation
Which Parameters to Optimise?
Optimisation is Expensive
Overfitting
Model Selection
Cross Validation
Grid Search
Optimising Strategies
Intraday Mean Reverting Pairs
Parameter Adjustment
Visualisation