لایب سان

Author(s): Sebastien Donadio, Sourav Ghosh

Publisher: Packt Publishing, Year: 2019

ISBN: 978-1789348347

Table of Contents Preface 1 Section 1: Introduction and Environment Setup Chapter 1: Algorithmic Trading Fundamentals 7 Why are we trading? 8 Basic concepts regarding the modern trading setup 8 Market sectors 9 Asset classes 10 Basics of what a modern trading exchange looks like 12 Understanding algorithmic trading concepts 13 Exchange order book 14 Exchange matching algorithm 14 FIFO matching 15 Pro-rata matching 15 Limit order book 16 Exchange market data protocols 16 Market data feed handlers 17 Order types 17 IOC – Immediate Or Cancel 17 GTD – Good Till Day 17 Stop orders 17 Exchange order entry protocols 18 Order entry gateway 18 Positions and profit and loss (PnL) management 18 From intuition to algorithmic trading 19 Why do we need to automate trading? 19 Evolution of algorithmic trading – from rule-based to AI 20 Components of an algorithmic trading system 22 Market data subscription 23 Limit order books 23 Signals 24 Signal aggregators 24 Execution logic 24 Position and PnL management 25 Risk management 26 Backtesting 26 Why Python? 27 Choice of IDE – Pycharm or Notebook 28 Table of Contents [ ii ] Our first algorithmic trading (buy when the price is low, and sell when the price is high) 29 Setting up your workspace 29 PyCharm 101 30 Getting the data 30 Preparing the data – signal 31 Signal visualization 34 Backtesting 35 Summary 37 Section 2: Trading Signal Generation and Strategies Chapter 2: Deciphering the Markets with Technical Analysis 39 Designing a trading strategy based on trend- and momentum-based indicators 40 Support and resistance indicators 40 Creating trading signals based on fundamental technical analysis 47 Simple moving average 47 Implementation of the simple moving average 48 Exponential moving average 49 Implementation of the exponential moving average 51 Absolute price oscillator 53 Implementation of the absolute price oscillator 53 Moving average convergence divergence 55 Implementation of the moving average convergence divergence 56 Bollinger bands 59 Implementation of Bollinger bands 60 Relative strength indicator 62 Implementation of the relative strength indicator 63 Standard deviation 66 Implementing standard derivatives 66 Momentum 68 Implementation of momentum 69 Implementing advanced concepts, such as seasonality, in trading instruments 71 Summary 79 Chapter 3: Predicting the Markets with Basic Machine Learning 80 Understanding the terminology and notations 81 Exploring our financial dataset 84 Creating predictive models using linear regression methods 87 Ordinary Least Squares 87 Regularization and shrinkage – LASSO and Ridge regression 93 Decision tree regression 94 Creating predictive models using linear classification methods 95 K-nearest neighbors 95 Support vector machine 98 Table of Contents [ iii ] Logistic regression 99 Summary 100 Section 3: Algorithmic Trading Strategies Chapter 4: Classical Trading Strategies Driven by Human Intuition 102 Creating a trading strategy based on momentum and trend following 103 Examples of momentum strategies 104 Python implementation 104 Dual moving average 104 Naive trading strategy 107 Turtle strategy 109 Creating a trading strategy that works for markets with reversion behavior 111 Examples of reversion strategies 112 Creating trading strategies that operate on linearly correlated groups of trading instruments 112 Summary 130 Chapter 5: Sophisticated Algorithmic Strategies 131 Creating a trading strategy that adjusts for trading instrument volatility 132 Adjusting for trading instrument volatility in technical indicators 132 Adjusting for trading instrument volatility in trading strategies 133 Volatility adjusted mean reversion trading strategies 134 Mean reversion strategy using the absolute price oscillator trading signal 134 Mean reversion strategy that dynamically adjusts for changing volatility 144 Trend-following strategy using absolute price oscillator trading signal 148 Trend-following strategy that dynamically adjusts for changing volatility 153 Creating a trading strategy for economic events 155 Economic releases 156 Economic release format 157 Electronic economic release services 157 Economic releases in trading 158 Understanding and implementing basic statistical arbitrage trading strategies 161 Basics of StatArb 161 Lead-lag in StatArb 162 Adjusting portfolio composition and relationships 162 Infrastructure expenses in StatArb 163 StatArb trading strategy in Python 164 StatArb data set 164 Defining StatArb signal parameters 166 Defining StatArb trading parameters 167 Quantifying and computing StatArb trading signals 168 StatArb execution logic 172 Table of Contents [ iv ] StatArb signal and strategy performance analysis 173 Summary 183 Chapter 6: Managing the Risk of Algorithmic Strategies 184 Differentiating between the types of risk and risk factors 185 Risk of trading losses 185 Regulation violation risks 186 Spoofing 186 Quote stuffing 187 Banging the close 188 Sources of risk 188 Software implementation risk 188 DevOps risk 189 Market risk 190 Quantifying the risk 191 The severity of risk violations 192 Differentiating the measures of risk 193 Stop-loss 194 Max drawdown 196 Position limits 198 Position holding time 200 Variance of PnLs 201 Sharpe ratio 203 Maximum executions per period 204 Maximum trade size 207 Volume limits 207 Making a risk management algorithm 208 Realistically adjusting risk 213 Summary 222 Section 4: Building a Trading System Chapter 7: Building a Trading System in Python 224 Understanding the trading system 225 Gateways 226 Order book management 228 Strategy 230 Order management system 231 Critical components 232 Non-critical components 232 Command and control 233 Services 234 Building a trading system in Python 234 LiquidityProvider class 236 Strategy class 239 OrderManager class 245 MarketSimulator class 250 Table of Contents [ v ] TestTradingSimulation class 252 Designing a limit order book 255 Summary 263 Chapter 8: Connecting to Trading Exchanges 264 Making a trading system trade with exchanges 264 Reviewing the Communication API 266 Network basics 267 Trading protocols 267 FIX communication protocols 269 Price updates 269 Orders 271 Receiving price updates 272 Initiator code example 275 Price updates 275 Sending orders and receiving a market response 279 Acceptor code example 281 Market Data request handling 282 Order 283 Other trading APIs 286 Summary 287 Chapter 9: Creating a Backtester in Python 288 Learning how to build a backtester 288 In-sample versus out-of-sample data 289 Paper trading (forward testing) 290 Naive data storage 290 HDF5 file 291 Databases 293 Relational databases 293 Non-relational databases 295 Learning how to choose the correct assumptions 296 For-loop backtest systems 298 Advantages 299 Disadvantages 299 Event-driven backtest systems 299 Advantages 300 Disadvantages 301 Evaluating what the value of time is 302 Backtesting the dual-moving average trading strategy 306 For-loop backtester 306 Event-based backtester 310 Summary 319 Section 5: Challenges in Algorithmic Trading Chapter 10: Adapting to Market Participants and Conditions 321 Table of Contents [ vi ] Strategy performance in backtester versus live markets 322 Impact of backtester dislocations 324 Signal validation 325 Strategy validation 325 Risk estimates 325 Risk management system 326 Choice of strategies for deployment 326 Expected performance 326 Causes of simulation dislocations 327 Slippage 327 Fees 327 Operational issues 328 Market data issues 328 Latency variance 328 Place-in-line estimates 329 Market impact 329 Tweaking backtesting and strategies in response to live trading 330 Historical market data accuracy 330 Measuring and modeling latencies 331 Improving backtesting sophistication 332 Adjusting expected performance for backtester bias 333 Analytics on live trading strategies 334 Continued profitability in algorithmic trading 335 Profit decay in algorithmic trading strategies 335 Signal decay due to lack of optimization 336 Signal decay due to absence of leading participants 336 Signal discovery by other participants 337 Profit decay due to exit of losing participants 338 Profit decay due to discovery by other participants 338 Profit decay due to changes in underlying assumptions/relationships 339 Seasonal profit decay 340 Adapting to market conditions and changing participants 341 Building a trading signals dictionary/database 341 Optimizing trading signals 343 Optimizing prediction models 344 Optimizing trading strategy parameters 344 Researching new trading signals 345 Expanding to new trading strategies 347 Portfolio optimization 348 Uniform risk allocation 349 PnL-based risk allocation 349 PnL-sharpe-based risk allocation 349 Markowitz allocation 350 Regime Predictive allocation 351 Incorporating technological advances 353 Summary 354 Final words 355 Other Books You May Enjoy 356 Table of Contents [ vii ] Index 359

برای ارسال نظر لطفا وارد شوید یا ثبت نام کنید