Practical Python for Algorithmic Trading

Course details

If you work in finance or have any interest in investing and trading, you know that there’s a treasure trove of financial data available to you at any moment. But how can you use all that information to your advantage? Algorithmic trading using machine learning techniques can help you make trading decisions based on data. In this course, Jesus Lopez teaches you about data preprocessing, feature engineering, and how to use advanced machine learning models to enhance your trading strategies. He shows you how to download stock market data from Yahoo Financeto be trained on machine learning models that predict the future, and how to create investment decisions based on the predictions. Learn how to optimize your strategies, understand backtesting techniques, and interpret performance reports with confidence.

Concepts

0. Introduction

01 - Algorithmic trading using machine learning
02 - Maximize your learning

1. Working with Stock Market Data

03 - Download and export data
04 - Filter rows and create columns for trading strategies

2. Backtesting with Classification Models

05 - Compute machine learning classification model
06 - First configurations of the strategy class
07 - Simulate the investment strategy step by step
08 - Run the backtest on the strategy
09 - Challenge - Backtest with other tickers

3. Backtesting with Regression Models

10 - Compute machine learning regression model
11 - How to evaluate regression models
12 - Configure and run the backtest with the regression model
13 - How to interpret the backtesting dashboard

4. Backtesting Optimization

14 - Optimizing strategy parameters
15 - Pandas reporting with heatmaps
16 - Smart optimization to save computing time
17 - Challenge - Optimization with other datasets

5. The Overfitting Problem in Backtesting

18 - Why machine learning models overfit the data
19 - How to train models within the backtest
20 - Challenge - Train test with other tickers
21 - Walk forward validation in machine learning
22 - Anchored walk forward validation in backtesting
23 - Create library for backtesting strategies
24 - Interpret reports from walk forward validation approaches
25 - Challenge - Walk forward with other tickers

Conclusion

26 - Course summary
27 - What's next