You already know python, and you want to monetize and diversify your knowledge?
You already have some trading knowledge, and you want to learn about artificial intelligence in algorithmic trading?
You are simply a curious person who wants to get into this subject?
If you answer at least one of these questions, I welcome you to this course. For beginners in python, don’t panic! There is a python course (small but condensed) to master this python knowledge.
In this course, you will learn how to program strategies from scratch. Indeed, after a crash course in Python, you will learn how to implement a system based on Deep Learning (Deep neural network, Recurrent neural network).
Once the strategies are created, we will backtest them using python. So that we know better this strategy using statistics like Sortino ratio, drawdown the beta… Then we will put our best algorithm in live trading.
You will learn about tools used by both portfolio managers and professional traders:
-
Artificial intelligence algorithm
-
Apply Deep Learning in Live Trading
-
Predict stock prices using Deep Learning
-
Live trading implementation
-
Import financial data using MetaTrader 5 or Yahoo finance
-
DNN Algorithm
-
RNN algorithm to analyze and predict time series behavior
-
How to do a backtest a strategy using the programming language Python
-
Numpy, Pandas, Matplotlib
-
Sharpe, Sortino ratios
-
Alpha, Beta coefficients
Why this course and not another?
-
It is not a programming course nor a trading course. It is a course in which programming is used for trading.
-
A data scientist does not create this course, but a degree in mathematics and economics specialized in Machine learning for finance.
-
You can ask questions or read our quantitative finance articles simply by registering on our free Discord forum.
Without forgetting that the course is satisfied or refunded for 30 days. Don’t miss an opportunity to improve your knowledge of this fascinating subject.
Python basics
Python for data science
-
3Introduction
-
4Type of object: Number
-
5Type of object: String
-
6Type of object: Logical operations / Boolean
-
7Type of object: Variable assignment
-
8Type of object: Tuple and list
-
9Type of object: Dictionary
-
10Type of object: Set
-
11Python structures: IF / ELIF / ELSE
-
12Python structures: FOR
-
13Python structures: WHILE
-
14Functions: Basics of function
-
15Functions: Local variable
-
16Functions: Global variable
-
17Functions: Lambda function
Import and manage the data
Features engineering
Deep Neural Networks apply to algorithmic trading
Vectorized backtesting
-
37Introduction
-
38Quick recap of the DNN theory
-
39Data import & Features engineering
-
40Train / Test set split (to fit the DNN model)
-
41Why and how to standardize the features
-
42Create a DNN using Tensorflow 2.0
-
43Use the DNN predictions to create a trading strategy
-
44Automate the process
-
45The stochastic initialization problem
-
46How to fix the stochastic initialization problem
-
47Bagging method using the different ANNs
Recurrent Neural Networks for algorithmic trading
MetaTrader 5 live trading using Python
-
57Introduction
-
58Theory behind RNNs
-
59Recap from the DNN chapter
-
60How to transform 2-dimensional data into 3-dimensional data
-
61How to create a RNN using TensorFlow 2.0
-
62Dropout Layer
-
63RNN prediction to create a trading strategy
-
64Automate the process
-
65Find the best models throughout all the stochastic initialization