Difference between revisions of "Learning Algorithms for Trading"

From Quantitative Analysis Software Courses
Jump to navigation Jump to search
 
(5 intermediate revisions by the same user not shown)
Line 3: Line 3:
 
**Out of sample
 
**Out of sample
 
**Roll forward cross validation
 
**Roll forward cross validation
−
*Supervised ML
+
*ML methods we will use in this class
 +
**Linear regression
 +
**KNN regression
 +
**(Random Forest regression considering to drop)
 +
**Q-Learning
 +
*Supervised ML (intent is that the treatment here is light)
 
**Use: Regression
 
**Use: Regression
 
**Use: Classification
 
**Use: Classification
 
**Model type: Parametric
 
**Model type: Parametric
 
**Model type: Instance-based
 
**Model type: Instance-based
−
*Reinforcement Learning
+
*Introduce the problem we will focus on in the rest of the class, namely:
−
**Use: Find a policy
+
**Example data, will learn on over a particular year (2012)
−
*Overview: LinReg, KNN, Decision Trees, Q-Learning
+
**Will test on over the next two years (2013 2014)
 +
**It will be "easy" data that has obvious patterns
 +
**You will create trades.txt and run them through your backtester
  
 
==Lesson 2: Q-Learning and Dyna==
 
==Lesson 2: Q-Learning and Dyna==
 
*Long/short
 
*Long/short
 +
*Overview of use and backtesting
 +
**Out of sample
 +
**Roll forward cross validation
 +
*Supervised ML (intent is that the treatment here is light)
 +
**Use: Regression
 +
**Use: Classification
 +
**Model type: Parametric
 +
**Model type: Instance-based
 +
*Reinforcement Learning (light)
 +
**Use: Find a policy
 +
*Introduce the problem we will focus on in the rest of the class, namely:
 +
**Example data, will learn on over a particular year (2012)
 +
**Will test on over the next two years (2013 2014)
 +
**It will be "easy" data that has obvious patterns
 +
**You will create trades.txt and run them through your backtester
 +
*Overview: LinReg, KNN, Decision Trees, Q-Learning
  
 
==Lesson 3: Time series prediction as an ML problem==
 
==Lesson 3: Time series prediction as an ML problem==

Latest revision as of 13:37, 14 July 2015

Lesson 1: How Machine Learning is used at a hedge fund

  • Overview of use and backtesting
    • Out of sample
    • Roll forward cross validation
  • ML methods we will use in this class
    • Linear regression
    • KNN regression
    • (Random Forest regression considering to drop)
    • Q-Learning
  • Supervised ML (intent is that the treatment here is light)
    • Use: Regression
    • Use: Classification
    • Model type: Parametric
    • Model type: Instance-based
  • Introduce the problem we will focus on in the rest of the class, namely:
    • Example data, will learn on over a particular year (2012)
    • Will test on over the next two years (2013 2014)
    • It will be "easy" data that has obvious patterns
    • You will create trades.txt and run them through your backtester

Lesson 2: Q-Learning and Dyna

  • Long/short
  • Overview of use and backtesting
    • Out of sample
    • Roll forward cross validation
  • Supervised ML (intent is that the treatment here is light)
    • Use: Regression
    • Use: Classification
    • Model type: Parametric
    • Model type: Instance-based
  • Reinforcement Learning (light)
    • Use: Find a policy
  • Introduce the problem we will focus on in the rest of the class, namely:
    • Example data, will learn on over a particular year (2012)
    • Will test on over the next two years (2013 2014)
    • It will be "easy" data that has obvious patterns
    • You will create trades.txt and run them through your backtester
  • Overview: LinReg, KNN, Decision Trees, Q-Learning

Lesson 3: Time series prediction as an ML problem

[note: need to create fake stock data that has embedded patterns]

Lesson 4: Learner APIs

Lesson 5: Linear regression

Lesson 6: KNN

Lesson 7: Assessing a learning algorithm

  • Now that we have two, (linreg & KNN), let's compare them
  • RMS error
  • Scatterplot predict vs actual
  • Corrcoef

Lesson 8: Overfitting

Lesson 9: Decision trees

Lesson 10: Ensemble learners & bagging

Lesson 11: Random trees & forests

Retrieved from "http://quantsoftware.gatech.edu/index.php?title=Learning_Algorithms_for_Trading&oldid=214"