The Artificial Intelligence for Trading Udacity course is a 6 month course focused on learning the basics of quantitative analysis, trade signal generation and portfolio management. The repository will contain all of the projects and exercises completed by myself towards the completion of the course.
This course is broken down into two terms each with four projects and various exercises:
- Quantitative Trading - Learn the basics of quantitative analysis, including data processing, trading signal generation, and portfolio management. Use Python to work with historical stock data, develop trading strategies, and construct a multi-factor model with optimization
- AI Algorithms in Trading - Learn how to analyze alternative data and use machine learning to generate trading signals. Run a backtest to evaluate and combine top performing signals
The projects completed over the entire course are:
- Trading With Momentum - implement a momentum trading strategy and determine whether it has the potential to be profitable
- Breakout Strategy - code and evaluate a breakout signal, including finding outliers within a trading signal
- Smart Beta and Portfolio Optimisation - create two portfolios that use smart beta methodology and optimisation, and calculate the turnover of the portfolio
- Multi-Factor Model - research and generate multiple alpha factors, followed by the evaluation of the performance of those alpha factors to choose the optimal one for the portfolio
- Sentiment Analysis Using NLP - apply NLP to corporate filings (10Q and 10K statements) to decide which company to invest in
- Sentiment Analysis With Neural Networks - build a deep neural network to process and interpret news data
- Combine Signals For Enchanced Alpha - combine signals on a random forest for enchanced alpha
- Backtesting - build a backtester that uses Barra data, this will perform portfolio optimisation with computational efficiency in mind. Use performance attribution to identify the major drivers of your portfolios profit and loss
All coding is completed in Python using Jupyter notebooks