Quant Trading using Machine Learning : Online course

About Course

• Prerequisites: Working knowledge of Python is necessary if you want to run the source code that is provided. Basic knowledge of machine learning, especially ML classification techniques, would be helpful but it's not mandatory.

  This course takes a completely practical approach to applying Machine Learning techniques to Quant Trading

  Completely Practical: This course has just enough theory to get you started with both Quant Trading and Machine Learning. The focus is on practically applying ML techniques to develop sophisticated Quant Trading models. From setting up your own historical price database in MySQL to writing hundreds of lines of Python code, the focus is on doing from the get go.

  Machine Learning Techniques: We'll cover a variety of machine learning techniques, from K-Nearest Neighbors and Decision Trees to pretty advanced techniques like Random Forests and Gradient Boosted Classifiers. But, in practice Machine Learning is not just about the algorithms. Feature Engineering, Parameter Tuning, Avoiding overfitting; these are all a part and parcel of developing Machine Learning applications and we do it all in this course. 

  Quant Trading: Quant Trading is a perfect example of an area where the use of Machine Learning leads to a step change in the quality of the models used. Traditional models often depend on Excel and building sophisticated models requires a huge amount of manual effort and domain knowledge. Machine Learning libraries available today allow you to build highly sophisticated models that give you much better performance with much less effort. 

Curriculam

• Section 1: You, This Course and Us
  	Lecture 1	You, This Course and Us	02:00
  Section 2: Developing Trading Strategies in Excel
  	Lecture 2	Are markets efficient or inefficient?	10:27
  	Lecture 3	Momentum Investing	11:31
  	Lecture 4	Mean Reversion	06:30
  	Lecture 5	Evaluating Trading Strategies - Risk And Return	16:22
  	Lecture 6	Evaluating Trading Strategies - The Sharpe Ratio	10:16
  	Lecture 7	The 2 Step process - Modeling and Backtesting	03:48
  	Lecture 8	Developing a Trading Strategy in Excel	11:42
  Section 3: Setting up your Development Environment
  	Lecture 9	Installing Anaconda for Python	09:00
  	Lecture 10	Installing Pycharm - a Python IDE	03:55
  	Lecture 11	MySQL Introduced and Installed (Mac OS X)	07:03
  	Lecture 12	MySQL Server Configuration and MySQL Workbench (Mac OS X)	17:32
  	Lecture 13	MySQL Installation (Windows)	06:31
  Section 4: Setting up a Price Database
  	Lecture 14	Programmatically Downloading Historical Price Data Preview	06:23
  	Lecture 15	CodeAlong - Dowloading Price data from Yahoo Finance	14:39
  	Lecture 16	CodeAlong - Downloading a URL in Python	07:38
  	Lecture 17	CodeAlong - Downloading Price data from the NSE	13:55
  	Lecture 18	CodeAlong - Unzip and process the downloaded files	05:21
  	Lecture 19	Manually download data for 10 years	Article
  	Lecture 20	CodeAlong - Download Historical Data for 10 years	06:26
  	Lecture 21	Inserting the Downloaded files into a Database	10:10
  	Lecture 22	CodeAlong - Bulk loading downloaded files into MySQL tables	15:12
  	Lecture 23	Data Preparation	04:16
  	Lecture 24	CodeAlong - Data Preparation	12:43
  	Lecture 25	Adjusting for Corporate Actions	08:41
  	Lecture 26	CodeAlong - Adjusting for Corporate Actions 1	15:29
  	Lecture 27	CodeAlong - Adjusting for Corporate Actions 2	08:47
  	Lecture 28	CodeAlong - Inserting Index prices into MySQL	05:40
  	Lecture 29	CodeAlong - Constructing a Calendar Features table in MySQL	06:53
  Section 5: Decision Trees, Ensemble Learning and Random Forests
  	Lecture 30	Planting the seed - What are Decision Trees?	17:00
  	Lecture 31	Growing the Tree - Decision Tree Learning	18:03
  	Lecture 32	Branching out - Information Gain	18:51
  	Lecture 33	Decision Tree Algorithms	07:49
  	Lecture 34	Overfitting - The Bane of Machine Learning	19:03
  	Lecture 35	Overfitting Continued	11:19
  	Lecture 36	Cross Validation	18:55
  	Lecture 37	Regularization	07:18
  	Lecture 38	The Wisdom Of Crowds - Ensemble Learning	16:39
  	Lecture 39	Ensemble Learning continued - Bagging, Boosting and Stacking	18:02
  	Lecture 40	Random Forests - Much more than trees	12:28
  Section 6: A Trading Strategy as Machine Learning Classification
  	Lecture 41	Defining the problem - Machine Learning Classification	15:51
  Section 7: Feature Engineering
  	Lecture 42	Know the basics - A Pandas tutorial	11:41
  	Lecture 43	CodeAlong - Fetching Data from MySQL	18:34
  	Lecture 44	CodeAlong - Constructing some simple features	07:27
  	Lecture 45	CodeAlong - Constructing a Momentum Feature	08:42
  	Lecture 46	CodeAlong - Constructing a Jump Features	05:52
  	Lecture 47	CodeAlong - Assigning Labels	03:12
  	Lecture 48	CodeAlong - Putting it all together	18:08
  	Lecture 49	CodeAlong - Include support features from other tickers	06:34
  Section 8: Engineering a Complex Feature - A Categorical Variable with Past Trends
  	Lecture 50	Engineering a Categorical Variable	03:49
  	Lecture 51	CodeAlong - Engineering a Categorical Variable	06:46
  Section 9: Building a Machine Learning Classifier in Python
  	Lecture 52	Introducing Scikit-Learn	03:33
  	Lecture 53	Introducing RandomForestClassifier	09:25
  	Lecture 54	Training and Testing a Machine Learning Classifier	15:01
  	Lecture 55	Compare Results from different Strategies	05:44
  	Lecture 56	Using Class probabilities for predictions	03:11
  Section 10: Nearest Neighbors Classifier
  	Lecture 57	A Nearest Neighbors Classifier	06:49
  	Lecture 58	CodeAlong - A nearest neighbors Classifier	04:16
  Section 11: Gradient Boosted Trees
  	Lecture 59	What are Gradient Boosted Trees?	12:38
  	Lecture 60	Introducing XGBoost - A python library for GBT	11:51
  	Lecture 61	CodeAlong - Parameter Tuning for Gradient Boosted Classifiers Preview	09:21
  Section 12: Introduction to Quant Trading
  	Lecture 62	Financial Markets - Who are the players?	16:38
  	Lecture 63	What is a Stock Market Index?	03:13
  	Lecture 64	The Mechanics of Trading - Long vs Short positions	11:56
  	Lecture 65	Futures Contracts	14:25

What you will get from this course?

• • Develop Quant Trading models using advanced Machine Learning techniques
  • Compare and evaluate strategies using Sharpe Ratios
  • Use techniques like Random Forests and K-Nearest Neighbors to develop Quant Trading models
  • Use Gradient Boosted trees and tune them for high performance
  • Use techniques like Feature engineering, parameter tuning and avoiding overfitting
  • Build an end-to-end application from data collection and preparation to model selection

  • Quant Trading : Financial Markets, Stocks, Indices, Futures, Return, Risk, Sharpe Ratio, Momentum Investing, Mean Reversion, Developing trading strategies using Excel, Backtesting

  • Machine Learning: Decision Trees, Ensemble Learning, Random Forests, Gradient Boosted Classifiers, Nearest Neighbors, Feature engineering, Overfitting, Parameter Tuning

  • MySQL: Set up a historical price database in MySQL using Python. 

  • Python Libraries : Pandas, Scikit-Learn, XGBoost, Hyperopt

    A Note on Python: The code-alongs in this class all use Python 2.7. Source code (with copious amounts of comments) is attached as a resource with all the code-alongs.

     

Who should buy this course?

• • Quant traders who have not used Machine learning techniques before to develop trading strategies
  • Analytics professionals, modelers, big data professionals who want to get hands-on experience with Machine Learning
  • Anyone who is interested in Machine Learning and wants to learn through a practical, project-based approach
  • Working knowledge of Python is necessary if you want to run the source code that is provided.