Neural Networks in Trading by Dr. Ernest P. Chan
$72.00
Author: Dr. Ernest P. Chan
File size: 407 MB
Media Type: Online Course
Delivery Time: 1-12 hours.
Content proof: Watch here!
- Description
Description
Neural Networks in Trading by Dr. Ernest P. Chan – Instant download!
Recommended for programmers and quants to implement neural network and deep learning in financial markets. Offered by Dr. Ernest Chan, learn to use advanced techniques such as LSTM, RNN in live trading.
LIVE TRADING
- Explain what a neural network is and how it works
- Code a neural network model using Sklearn
- Describe a Deep Neural Network
- List the various activation functions used
- Code a market trend predicting strategy
- Describe a Recurrent Neural Network
- Analyze an LSTM cell and its working
- Code a market close-price predicting strategy
- Perform a cross-validation to tune the hyper-parameters of a deep learning model
- Paper trade and live trade your strategies without any installations or downloads
SKILLS COVERED
Math Concepts
|
Machine Learning
|
Python
|
PREREQUISITES
You should have a basic knowledge of machine learning algorithms and training and testing datasets. These concepts are covered in our free course ‘Introduction to Machine Learning’. Prior experience in programming is required to fully understand the implementation of Artificial Intelligence techniques covered in the course. However, Python programming knowledge is optional. If you want to be able to code and implement the machine learning strategies in Python, you should be able to work with ‘Dataframes’ and ‘Sklearn’ library. Some of these skills are covered in the course ‘Python for Trading’.
SYLLABUS
Neural Networks in Trading by Dr. Ernest P. Chan, what is it included (Content proof: Watch here!)
- Introduction – 3m 54s
- Quantra Features and Guidance – 4m 9s
- Neural Networks Intuition – 1m 55s
- Linear Regression Revisited – 3m
- Hidden Layers – 2m
- Structure of a Neural Network – 2m
- Understanding Forward Propagation – 10m
- Forward Propagation Mechanism – 2m
- Backpropagation – 2m 56s
- Calculate the MSE – 2m
- Identify Loss Functions – 2m
- Loss Optimisation – 2m
- Identify Optimisation Method – 2m
- Function Derivative Chain Rule – 10m
- Identify Derivative Equation – 2m
- Math behind Back-Propagation – 10m
- Implement a MLPClassifier – 2m 26s
- Identify the Sigmoid Graph – 2m
- Output of a Sigmoid Function – 2m
- How to Use Jupyter Notebook? – 1m 54s
- MLPClassifier Hands-on – 10m
- Import Boeing Co Data – 5m
- Define Predictor Variable – 5m
- Calculate Future Returns – 5m
- Define Target Variable – 5m
- Train-Test Split – 5m
- Feature Scaling – 5m
- Loss Optimisation Algorithm – 2m
- What is Sigmoid? – 2m
- Hidden Layer Sizes – 2m
- MLPClassifier Definition – 5m
- Predict Market Movement – 5m
- Generate Evaluation Metrics – 2m
- Live Trading on Blueshift
- Live Trading Template
- Deep Learning in Trading
- Recurrent Neural Networks
- Long Short Term Memory Unit (LSTMs)
- Cross Validation in Keras
- Challenges in Live Trading
- Python Installation
- Paper and Live Trading
- Downloadable Resources
WHY QUANTRA?
 |
 |
 |
 |
USER TESTIMONIALS
| Abinash Tripathy
Accountant at HCL Peripherals, India Let me explain why I gave this course 5 stars. When I first bought this course, it lacked the implementation section. I complained about it and they fixed it, thereby actually making the course worth for me. Thank you very much Team Quantra. |
Sergei Cherkasov
Trader, Russia I had two Dr. Chans courses on artificial intelligence and I want to rate them as really good. For me it was a good start in machine learning. Learned a lot here as these courses are made well. My very big desire for these courses is to have paper/real trading examples for every strategy and model that was in the course, as it will help learners to learn faster and prosper at trading! |
Sergei Belov
United States |
