Machine Learning for Algorithmic Trading Bots with Python

In this video, you will become familiar with the basics of decision trees, random forests, and ensemble learning.

   •  Study the mathematics and algorithm criteria for building decision trees

   •  Introduce ensemble learning bootstrap aggregation (bagging)

   •  Highlight the difference between classification and regression trees

In this video, you shall learn how to implement random forests for stock price forecasting using SciKit-Learn machine learning library in Python.

   •  Feature engineering for stock price model

   •  Fine-tuning the parameters of Random Forests Regressor model

   •  Train and export the model using JobLib

In this video, you shall integrate the trained model into the existing trading bot skeletion and learn how to import models and use them forecasting during a trading session.

   •  Import trained random forests Regressor model

   •  Design a trading strategy that forecasts stock price before making decisions

   •  Run the Backtest session

In this video, you are going to analyze the Backtest session performance report using Jupyter Notebook. You will learn new econometric fundamentals and understand the different evaluation metrics.

   •  Import the performance report in a Jupyter Notebook

   •  Plot and analyze performance

   •  Understand econometric evaluation metrics available in Zipline

In this video, you will become familiar with the basics of online streaming algorithms and learn the mechanisms of the one-pass algorithms.

• Explain online algorithms terminology, basics, advantages, and requirements

• Understand the mechanism of one-pass algorithms

In this video, you shall learn correlation analysis in statistics, auto-correlation trading strategy, and pairs trading strategy.

• Dive into the mathematics of correlation analysis

• Learn how the auto-correlation trading strategy works

• Learn how the pairs trading strategy works

In this video, you shall build the auto-correlation trading strategy into our algorithmic trading bot and learn more about the Zipline APIs.

• Design and implement the Auto-Correlation Strategy with Python

• Configure Zipline run_algorithm method

• Run the strategy and plot portfolio value over time

In this video, you are going to analyze the performance reports using Jupyter Notebook. You will also learn more econometric evaluation methods and techniques.

• Import the performance report

• Analyze and plot econometric indicators

• Understand the interpretation of more econometric indicators and what each one of them means

In this video, you will become familiar with the basics of boosting, gradient boosting, and time series cross validation.

• What is boosting in ensemble learning?

• What is gradient boosting and how is it related to gradient descent?

• What is cross validation? Introduce variants of cross validation for time series forecasting.

In this video, you shall implement gradient boosting using SciKit-Learn with Time Series Split.

• Feature engineering of price model data using Pandas

• Implement time series cross validation with SciKit-Learn

• Train and export a gradient boosting model

In this video, you shall understand the evaluation metrics for machine learning models with cross validation.

• Evaluate cross validation loss and accuracy

• Visualize train test splits for SciKit-Learn time series split

In this video, you will become familiar with the basics of scalp trading and indicators signals.

• What is scalp trading?

• How to implement scalp trading with indicator signals and bollinger bands?

• What is Sharpe Ratio?

In this video, you shall implement scalp trading with two indicator signals and bollinger bands.

• Implement scalp trading class

• Import BitCoin and Ethereum securities custom dataset into Zipline

• Run Backtest session for scalp trading with custom dataset

In this video, you shall understand the evaluation metrics for investment portfolio with Sharpe Ratio.

• Import performance report using Pandas and analyze econometric signals

• Analyze and visualize Sharpe Ratio

• Analyze and visualize accumulative returns

In this video, you will learn risk management fundamentals and how to calculate Value at Risk.

• Risk management process

• How to trigger Stop loss

• How to calculate VaR

In this video, you shall integrate VaR & stop loss into scalp trading with two indicator signals and bollinger bands.

• A quick refresher on historical simulation and model-based approaches to calculate VaR

• Calculate Conditional Value at Risk in Zipline trading sessions of Backtest simulation.

• Trigger stop loss and exit positions

In this video, we introduce support vector machines for both classification and regression, and how to use different kernel functions such as sigmoid and radial basis functions.

• Support Vector Machine and finding an optimal decision boundary

• Kernel functions and the difference between linearly separable and non-linearly separable datasets

• The mathematics derivation of support vector machines as primal dual optimization problem with Lagrange multipliers

In this video, you will code along the implementation of support vector regression with grid search cross validation for forecasting portfolio returns.

• Implement support vector regression and grid search cross validation with SciKit-Learn

• Import trained model and forecast portfolio returns during Zipline Backtest simulation

• Evaluate the Sharpe ratio and accumulative returns of the trading strategy

In this video, I bid you a farewell and give you some career hints for future applications of techniques learned throughout the course.

• Reference text books on financial machine learning

• Machine learning potentials in finance

• Your first internship goals and culture hints