We will create an algorithmic trading strategy that earns 50% annually.
Use numpy to do scientific calculation
Use pandas to import and organize data
Use Matplotlib to visualize data
Use, create, understand mathematical model
Machine learning for algorithmic trading
Features Engineering
Statistics for finance
Create an easy-to-reuse backtesting universe
Automatically take sales and buy positions
Data import with a API
It is with pride that I offer this data science course for algorithmic trading. It is the fruit of several years of work in the field to truly understand all the subtleties of the world of quantitative finance.
Using libraries will allow you to do complex mathematical calculations applied to finance in just a few lines of code. We will see how to create an algorithm for trading from data import to automatic positions. You will create an algorithm that will yield more than 50% annually on the Nasdaq 100 using an algorithm.
In summary, we will study:
The numpy library to do scientific calculations
The pandas library organize and visualize data
The Matplotlib library to make powerful graphics
Features engineering
Linear regression for finance
Machine vector support
Decision tree
Random Forest
Apply and understand the Sharpe ratio
Apply and understand the Sortino ratio
Understanding the volatility of a stock market asset
Understand and create a backtesting universe that is easy to use
Backtest the strategy using the most know metrics in trading
How to choose the best features for Machine Learning models
The basics in python language to follow the course and to do your own projects after the course.
The basics in python language to follow the course and to do your own projects after the course.
English
Language
Introduction
How to learn this course
Please read this
Install Anaconda environnement
Install a librairy
How to have the personal key?
Ressources
Basics of python
Variable
list
for
if
for/if
Summary
Python for finance
libraires
data import
Variation price
standard deviation / mean
pandas visualization
Matplotlib visualization
autocorrelation
Bonus: Moving average
Summary
Basics of trading
Stock market
Assets
cfd
spread
leverage
Summary
Statistics Stratégie for algorithmic trading
Introduction
Data import
Reorganize
Set of data
Linear regression
trading and prediction
Visualization
earning
Statistics
Summary
Backtesting
How understand this?
Starting
Initialization
Growth of investment
Statistics
Measures
Accuracy
Graphics
Summary
Data science for algorithmic trading
Data import
Variance Features Selection
Correlation features selection
Other features selection
Backtesting all variable
Backtesting best variable
Resume
Standardization
Summary
Machine Learning for algorithmic trading
Data import
Preprocessing
Linear SVR
Decision Tree Regressor
Random Forest Regressor
Summary
BONUS
Code for create a backtesting environnemnt
The post Data science for algorithmic trading appeared first on StudyBullet.