HKU FinTech Competition

This GitHub repo serves you as a directory for the whole learning process about cryptocurrency and algorithmic trading. Topics related to algorithmic trading will be discussed, such as motivations of adopting it (especially in the crypto market), an overview of knowledge required to start algotrading, and the general procedure of building algorithmic trading strategies.

This README provides a general picture of the upcoming tutorials aimed at equipping you with the necessary knowledge and skills to build and deploy your own algotrading strategy.

This module covers basic knowledge of cryptocurrency, trading and algorithmic trading.

• 0.1 What is a cryptocurrency?
• 0.2 What is trading?
• 0.3 Why trade cryptocurrency?
• 0.4 Algorithmic trading

This module covers all the necessary programming knowledge in python for the students to create their own trading algorithms.

• 1.1.1 Syntax
• 1.1.2 Functions
• 1.1.3 Booleans & Conditions
• 1.1.4 Lists
• 1.1.5 Loops and List comprehension
• 1.1.6 Strings and dictionaries
• 1.1.7 Working with External Libraries

• 1.2.1 Classes
• 1.2.2 Constructors and Instances
• 1.2.3 Methods
• 1.2.4 Objects as Arguments and Parameters
• 1.2.5 Inheritance (Optional)

This module covers basic data science and machine learning techniques with python, which can be applied to develop and enhance the trading algorithms.

• 2.1.1 Creating, Reading and Writing
  • Tutorial
  • Exercise (example)
• 2.1.2 Indexing, Selecting & Assigning
• 2.1.3 Summary Functions and Maps
• 2.1.4 Grouping and Sorting
• 2.1.5 Data Types and Missing Values
• 2.1.6 Renaming and Combining

• 2.2.1 How Models Work
• 2.2.2 Basic Data Exploration
• 2.2.3 Your First Machine Learning Model
• 2.2.4 Model Validation
• 2.2.5 Underfitting and Overfitting
• 2.2.6 Random Forests
• 2.2.7 Machine Learning Competition

This module covers basic quantitative finance knowledge, portfolio evaluation and examples of developing a simple trading algorithm.

• 3.1. Basic math of quantitative finance
• 3.2. Evaluation metrics for portfolio
• 3.3. Working with Quantconnect platform

This module covers the implementation of six basic trading strategies which you can directly apply on quantconnect and further enhance them.

• 4.1. Moving Average Trend Following
• 4.2. Bollinger Band Trend Following / Mean-reverting
• 4.3. Statistical Arbitrage
• 4.4. Gradient Boosting Decision Trees based Model
• 4.5. Deep Learning based Model
• 4.6. On-Chain Analysis