Share Description
Discover the fundamentals of quantitative analysis, such as data processing, trading signal generation, and portfolio management. Work with historical stock data in Python to create trading strategies and a multi-factor model with optimization.
Syllabus:
Course 1: Basic Quantitative Trading
- LESSON ONE-Introduction
- LESSON TWO-Stock Prices
- LESSON THREE-Market Mechanics
- LESSON FOUR-Data Processing
- LESSON FIVE-Stock Returns
- LESSON SIX-Momentum Trading
Project: Trading with Momentum
- In this project, you will learn how to put a momentum trading strategy into action and determine whether it has the potential to be profitable. You'll use historical data from a specific stock universe to generate a trading signal based on a momentum indicator. The signal will then be computed, and projected returns will be generated. Finally, you will conduct a statistical test to determine whether the signal contains alpha.
Course 2: Advanced Quantitative Trading
- LESSON ONE-Quant Workflow
- LESSON TWO-Outliers and Filtering Signals
- LESSON THREE-Regression
- LESSON FOUR-Time Series Modeling
- LESSON FIVE-Volatility
- LESSON SIX-Pairs Trading and Mean Reversion
Project: Breakout Strategy
- You will code and test a breakout signal in this project. You will perform statistical tests to determine normality and alpha. You will also learn how to identify outliers and assess the impact that filtered outliers may have on your trading signal. You will run various scenarios of your model with and without the outliers and decide whether or not to keep the outliers.
Course 3: Stocks, Indices, and ETFs
- LESSON ONE-Stocks, Indices and Funds
- LESSON TWO-ETFs
- LESSON THREE-Portfolio Risk and Return
- LESSON FOUR-Portfolio Optimization
Project: Smart Beta and Portfolio Optimization
- You will create two portfolios using smart beta methodology and optimization in this project. You will calculate tracking errors to assess the performance of the portfolios. You will also calculate your portfolio's turnover and determine the best time to rebalance.
- The portfolio weights will be determined by analyzing fundamental data and using quadratic programming.
Course 4: Factor Investing and Alpha Research
- LESSON ONE-Factors Models of Returns
- LESSON TWO-Risk Factor Models
- LESSON THREE-Alpha Factors
- LESSON FOUR-Advanced Portfolio Optimization with Risk and Alpha Factors Models
Project: Multi-factor Model
- In this project, you will investigate and generate a variety of alpha factors.
- Then you'll use a variety of techniques to assess the performance of your alpha factors and learn how to select the best ones for your portfolio. You will create an advanced portfolio optimization problem using constraints such as risk models, leverage, market neutrality, and factor exposure limits.
Course 5: Sentiment Analysis with Natural Language Processing
- LESSON ONE-Intro to Natural Language Processing
- LESSON TWO-Text Processing
- LESSON THREE-Feature Extraction
- LESSON FOUR-Financial Statements
- LESSON FIVE-Basic NLP Analysis
Project: Sentiment Analysis using NLP
- You will use Natural Language Processing on corporate filings such as 10Q and 10K statements in this project, from data cleaning and text processing to feature extraction and modelling. To generate company-specific sentiments, you will use bag-of-words and TF-IDF. You will decide which company to invest in and the best time to buy or sell based on the sentiments.
Course 6: Advanced Natural Language Processing with Deep Learning
- LESSON ONE-Introduction to Neural Networks
- LESSON TWO-Training Neural Networks
- LESSON THREE-Deep Learning with PyTorch
- LESSON FOUR-Recurrent Neural Networks
- LESSON FIVE-Embeddings & Word2Vec
- LESSON SIX-Sentiment Prediction RNN
Project: Sentiment Analysis with Neural Networks
- You will construct deep neural networks to process and interpret news data in this project. You will also experiment with various methods of embedding words into vectors. You will build and train LSTM networks for sentiment analysis. You will run backtests and apply the models to news data to generate signals.
Course 7: Combining Multiple Signals
- LESSON ONE-Overview
- LESSON TWO-Decision Trees
- LESSON THREE-Model Testing and Evaluation
- LESSON FOUR-Random Forests
- LESSON FIVE-Feature Engineering
- LESSON SIX-Overlapping Labels
- LESSON SEVEN-Feature Importance
Project: Combining Signals for Enhanced Alpha
- You will combine signals on a random forest to improve alpha in this project. You'll have to deal with the issue of overlapping samples while putting this together. We'll be using Quotemedia's end-of-day data and Sharadar's sector data for the dataset.
Course 8: Simulating Trades with Historical Data
- LESSON ONE-Intro to Backtesting
- LESSON TWO-Optimization with Transaction Costs
- LESSON THREE-Attribution
Project: Backtesting
- You will combine signals on a random forest to improve alpha in this project. You'll have to deal with the issue of overlapping samples while putting this together. We'll be using Quotemedia's end-of-day data and Sharadar's sector data for the dataset.
