Python for Finance and Algorithmic trading, 2nd edition: Machine Learning, Deep Learning, Time series Analysis, Risk and Portfolio Management for MetaTrader™5 Live Trading
- Length: 327 pages
- Edition: 1
- Language: English
- Publication Date: 2022-08-17
- ISBN-10: B0BB4SB3FV
- ISBN-13: 9798844126222
- Sales Rank: #826565 (See Top 100 Books)
The book presents the benefits of portfolio management, statistics and machine learning applied to live trading with MetaTrader™ 5.
This second version has allowed us to tweak some points of the existing chapters but especially to add 3 new chapters based on your feedbacks of the first version. So I am proud to offer you 3 new chapters: “Advanced backtest methods”, ”Features and target engineering” and ”From nothing to a live trading bot”.
- Learn portfolio management technics and how to implement your optimization criterion
- How to backtest a strategy using the most valuable metrics in trading
- Import data from your broker to be as close as possible to the market
- Learn statistical arbitrage through pair trading strategies
- Generate market predictions using machine learning, deep learning, and time series analysis
- Learn how to find the best take profit, stop loss, and leverage for your strategies
- Combine trading strategies using portfolio management to increase the robustness of the strategies
- Connect your Python algorithm to your MetaTrader 5 and run it with a demo or live trading account
- Use all codes in the book for live trading or screener if you prefer manual trading
Table of contents Why should you read this book? Chapter 1: Read me 1.1. Find the code 1.3. Join our community Chapter 2: Prerequisites 2.1. Mathematical prerequisites 2.1.1. Algebra 2.1.2. Statistics 2.1.3. Optimization 2.2. Prerequisites in finance 2.2.1. Market efficiency 2.2.2. Basics of trading 2.2.3. Basics of portfolio management 2.3. Prerequisites in Python 2.3.1. Libraries for data sciences 2.3.2. Libraries for finance 2.3.3. Libraries for mathematics Part 1: Portfolio management, risk management and backtesting Chapter 3: Static Portfolio management 3.1. Explanation behind portfolio optimization method 3.1.1. Systemic risk and specific risk 3.1.2. Diversification 3.2. The traditional portfolio optimization methods 3.2.1. Portfolio utility function 3.2.2. Mean-variance criterion 3.2.3. Mean-variance-skewness-kurtosis criterion 3.3. The modern portfolio optimization methods 3.3.1. Sharpe criterion 3.3.2. Sortino criterion Chapter 4: Tactical portfolio management 4.1. How dynamic methods works? 4.1.1. Short a stock 4.1.2. Momentum factor 4.1.3. Rebalancing 4.2. Moving average strategy 4.2.1. Moving average 4.2.2. Moving average factor 4.2.3. Build the strategy 4.3. Trend following strategy 4.3.1. Correlation 4.3.2. Trend following factor 4.3.3. Compute the strategy Chapter 5: Risk management and backtesting 5.1. The backtesting metrics 5.1.1. The CAPM metrics 5.1.2. Sharpe and Sortino 5.1.3. Drawdown 5.2. Risk management metrics 5.2.1. Value at risk (VaR) 5.2.2. Conditional Value at risk (cVaR) 5.2.3. Contribution risk 5.3. Automate the analysis 5.3.1. Create a function 5.3.2. Analyze static portfolio 5.3.3. Analyze dynamic portfolio Chapter 6: Advanced backtest methods 6.1 Useful backtest advice 6.1.1 Backtest is not a searching tool 6.1.2 Big days are not your friends 6.1.3 Understand your strategy 6.2 Compute the strategy returns using TP and SL 6.2.1 Find the extremum 6.2.2 Calculate the returns 6.2.3 Analyze the backtest 6.3 Advanced backtest tools 6.3.1 Backtest metrics list 6.3.2 Monte Carlo simulation 6.3.3 Easy Trailing stop Part 2: Statistics predictive models Chapter 7: Statistical arbitrage Trading 7.1. Stationarity to Cointegration 7.1.1. Stationarity 7.1.2. Cointegration 7.2. Pairs trading 7.2.1. How it works 7.2.2. Applications Chapter 8: Auto Regressive Moving Average model (ARMA) 8.1. Time series basics 8.1.1. Trend, cycle, seasonality 8.1.2. Log price properties 8.1.3. The linear regression 8.2. AR and MA models 8.2.1. Autoregressive model (AR) 8.2.2. Moving average model (MA) 8.3. ARMAs models 8.3.1. ARMA model 8.3.2. ARIMA model Chapter 9: Linear regression and logistic regression 9.1. Regression and classification 9.1.1. Reminder about regression 9.1.2. Understand the classification 9.2. Linear regression 9.2.1. Preparation of data 9.2.2. Implementation of the model 9.2.3. Predictions and backtest 9.3. Logistic regression 9.3.1. Preparation of data 9.3.2. Implementation of the model 9.3.3. Predictions and backtest Part 3: Machine learning, deep learning, live trading Chapter 10: Features and target engineering 10.1 Motivation and intuition 10.1.1 Features engineering 10.1.2 Target engineering 10.1.3 Why is it so important? 10.2 Trading application 10.2.1 Create trading indicators and useful trading features 10.2.2 Target labeling Chapter 11: Support vector machine (SVM) 11.1. Preparation of data 11.1.1. Features engineering 11.1.2. Standardization 11.2. Support Vector Machine Classifier (SVC) 11.2.1. Intuition about how works an SVC 11.2.2. How to create an SVC using Python 11.2.3. Predictions and backtest 11.3. Support Vector Machine Regressor (SVR) 11.3.1. Intuition about how works an SVR 11.3.2. How to create an SVR using Python 11.3.3. Predictions and backtest Chapter 12: Ensemble methods and decision tree 12.1. Decision tree 12.1.1. Decision Tree classifier 12.1.2. Decision tree regressor 12.1.3. Optimize the hyperparameters 12.2. Random Forest 12.2.1. Random Forest classifier 12.2.2. Random Forest Regressor 12.2.3. Optimize the hyperparameters 12.3. Ensemble methods 12.3.1. Voting method 12.3.2. Bagging method 12.3.3. Stacking method Chapter 13: Deep Neural Networks (DNN) 13.1. Intuition behind DNN 13.1.1. Forward propagation 13.1.2. Gradient descent 13.1.3. Backpropagation 13.2. DNN for classification 13.3.1. Preparation of data 13.2.2. Implementing a DNN for a classification task 13.2.3. Prediction and Backtest 13.3. DNN for regression 13.3.1. Implementing a DNN for a regression task 13.3.2. Custom loss function 13.3.3. Prediction and Backtest Chapter 14: Recurrent neural network 14.1 Principles of RNN 14.1.1. How an RNN works 14.1.2. LSTM neuron 14.1.3. GRU cell 14.2. RNN for classification 14.2.1. Transform 2d data to 3d data 14.2.2. Implementing the model 14.2.3. Prediction and backtest 14.3. RNN regressor 14.3.1. Precision about standardization 14.3.2. Implementing the model 14.3.3. Predictions and backtest Chapter 15: Bonus / Example of RNN with CNN (RCNN) 15.1. Intuition of CNN 15.2. Create an RCNN 15.3. Backtest Chapter 16: Real-life full project 16.1. Preparation of the data 16.1.1. Import the data 16.1.2. Features engineering 16.1.3. Train, test and validation sets 16.2. Modelling the strategy 16.2.1. Find the best assets 16.2.2. Combine the algorithms 16.2.3. Apply portfolio management technics 16.3. Find optimal take profit, stop loss and leverage 16.3.1. Optimal take profit (tp) 16.3.2. Optimal stop loss (sl) 16.3.3. Optimal leverage Chapter 17: From nothing to live trading 17.1 Trading strategies creation guidelines 17.1.1 The trading plan 17.1.2 The process of a trading strategy building 17.1.3 Trading journal 17.2 Do not put all your eggs in one basket 17.2.1 Bet sizing 17.2.2 Why create a trading strategy portfolio? 17.3. Live trading process 17.3.1. Safety first 17.3.2 Incubation phase 17.3.3 When to quit? Annex: Compounding versus simple interest What is the difference between the simple and the compounding methods? How to compute the simple and compounding interest Annex: Save and load scikit-learn and Tensorflow models Annex: MetaTrader class Additional readings
Donate to keep this site alive
To access the Link, solve the captcha.
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.