Skip to content

skharel/ML4T-Lecture-Notes

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

81 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

GA Tech ML4T - CS 7646 notes

Syllabus for Fall 2021 Course home

Love the course!

  • This is definitely a well done class; take this class before you get into other AI/ML classes. You will learn a lot from here that will make your life easy for other classes.
  • You will learn numpy, pandas, data cleaning and visualization in this course

Lecture video

Lecture is freely available for anyone!

https://omscs.gatech.edu/cs-7646-machine-learning-trading-course-videos

Notes

Week 1

Hello Numpy and pandas!

Week 2

Optimizations

  • Incomplete data: 1-5.ipynb
  • Histograms and scatter plots: 1-6.ipynb
    • Histograms and scatter plots
    • A closer lok at daily returns
    • What would it look like?
    • Histogram of daily returns
    • How to plot a histogram
    • Computing histogram statistics
    • Compare two histograms
    • Plot two histograms together
    • Scatter plots
    • Fitting a line to data points
    • Slope != correlation
    • Correlation vs slope
    • Scatter plots in python
    • Real world use of kurtosis
  • Sharpe ratio and other portfolio statistics: 1-7.ipynb
    • Overview
    • Daily Portfolio values
    • Portfolio Statistics
    • Which portfolio is better?
    • Sharpe Ratio
    • Form of the Sharpe Ratio
    • Computing Sharpie Ratio
  • Optimizers: Building a parameterized model: 1-8.ipynb
    • What is an optimizer?
    • Minimization example
    • Minimizer in pythong
    • How to defeat a minimizer
    • Convex Problems
    • Building a parameterized model
    • What is a good error metric?
    • Minimizers finds coefficients
    • Fit a line to given data points
    • And it works for polynomials too!

Week 3

Intro to ML

  • Optimizers: How to optimize a portfolio: 1-9.ipynb

    • What is portfolio optimization
    • The difference optimization can make
    • Which criteria is easiest to solve for?
    • Framing te problem
    • Ranges and constraints
  • How Machine Learning is used at a hedge fund: 3-1.ipynb

    • How Machine learning is used at a hedge fund overview
    • The ML problem
    • What's X and Y
    • Supervised Regression Learning
    • How it works with stock data
    • Example at a fintech company
    • Price forecasting demo
    • Backtesting
    • ML tool in use
    • Problems with regression
  • Regression: 3-2.ipynb

    • Regression Introduction
    • Parametric Regression
    • K Nearest Neighbor
    • How to predict
    • Kernel Regression
    • Parametric vs Non-parametric
    • Training and testing
    • Example for linear Regression

Week 4

Week 5

  • So you want to be a hedge fund manager? 2-1.ipynb

    • Types of funds
    • Liquidity and capitalization
    • What type of fund is it?
    • Incentives for fund managers
    • Two and twenty
    • How funds attract investors
    • Hedge fund goals and metrics
    • The computing inside a hedge fund
  • Market Mechanics: 2-2.ipynb

    • Market Mechanics Overview
    • What is in an order?
    • The order book
    • Up or down?
    • How orders affect the order book?
    • How orders get to the exchanges
    • How hedge funds exploit market mechanics
    • additional order types
    • Mechanics of short selling: Entry
    • Short Selling
    • Mechanics of short selling: Exit
    • What can go wrong?

Week 6

  • What is a company worth? 2-3.ipynb

    • What is a company worth?
    • Why company value matters?
    • The Balch Bond
    • The value of a future dollar
    • Intrinsic Value
    • Book Value
    • Market Capitalization
    • Why information affects stock price
    • Compute Company value
    • Would buy this stock?
  • The Capital Assets # Model (CAPM): 2-4.ipynb

    • The Capital Assets # Model
    • Definition of a portfolio
    • Portfolio return
    • The market portfolio
    • The CAPM Equation
    • Compare alpha and beta
    • CAPM vs active management
    • CAPM for portfolios
    • Implications of CAPM
    • Arbitrage # Theory

Week 7

  • How hedge funds use the CAPM: 2-5.ipynb

    • Risks for hedge funds
    • Two stock scenario
    • Two stock CAPM Math
    • Allocations remove market risk
    • How does it work
    • CAPM for hedge funds Summary
  • Technical Analysis: 2-6.ipynb

    • Technical versus fundamental analysis
    • Characteristics
    • Potential indicators
    • When is technical analysis valuable?
    • A few indicators:
      • Momentum
      • Simple Moving Average
      • Bollinger bands
    • Buy or Sell?
    • Normalization

Week 8

Week 9

About

GA tech ML4T lecture notes

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published