Difference between revisions of "Learning Algorithms for Trading"
Jump to navigation
Jump to search
| (11 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
| − | == | + | ==Lesson 1: How Machine Learning is used at a hedge fund== |
| − | *Regression | + | *Overview of use and backtesting |
| − | *Classification | + | **Out of sample |
| − | *Parametric | + | **Roll forward cross validation |
| − | *Instance-based | + | *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 | *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 | ||
| − | ==Time series prediction as an ML problem== | + | ==Lesson 3: Time series prediction as an ML problem== |
[note: need to create fake stock data that has embedded patterns] | [note: need to create fake stock data that has embedded patterns] | ||
| − | ==Learner APIs== | + | ==Lesson 4: Learner APIs== |
| − | ==Linear regression== | + | ==Lesson 5: Linear regression== |
| − | ==KNN== | + | ==Lesson 6: KNN== |
| − | ==Assessing a learning algorithm== | + | ==Lesson 7: Assessing a learning algorithm== |
*Now that we have two, (linreg & KNN), let's compare them | *Now that we have two, (linreg & KNN), let's compare them | ||
*RMS error | *RMS error | ||
| Line 24: | Line 53: | ||
*Corrcoef | *Corrcoef | ||
| − | ==Overfitting== | + | ==Lesson 8: Overfitting== |
| − | ==Decision trees== | + | ==Lesson 9: Decision trees== |
| − | ==Ensemble learners== | + | ==Lesson 10: Ensemble learners & bagging== |
| − | ==Random trees & forests== | + | ==Lesson 11: Random trees & forests== |
Latest revision as of 12:37, 14 July 2015
Contents
- 1 Lesson 1: How Machine Learning is used at a hedge fund
- 2 Lesson 2: Q-Learning and Dyna
- 3 Lesson 3: Time series prediction as an ML problem
- 4 Lesson 4: Learner APIs
- 5 Lesson 5: Linear regression
- 6 Lesson 6: KNN
- 7 Lesson 7: Assessing a learning algorithm
- 8 Lesson 8: Overfitting
- 9 Lesson 9: Decision trees
- 10 Lesson 10: Ensemble learners & bagging
- 11 Lesson 11: Random trees & forests
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
