Difference between revisions of "Learning Algorithms for Trading"
Jump to navigation
Jump to search
| Line 25: | Line 25: | ||
==Overfitting== | ==Overfitting== | ||
| + | |||
| + | ==Decision trees== | ||
| + | |||
| + | ==Decision forests== | ||
| + | |||
| + | ==Random trees & forests== | ||
| + | |||
| + | ==Artificial neural networks== | ||
Revision as of 00:02, 4 March 2015
Contents
- 1 Supervised machine learning
- 2 How ML fits into the computing at a hedge fund
- 3 Time series prediction as an ML problem
- 4 Learner APIs
- 5 Linear regression
- 6 KNN
- 7 Assessing a learning algorithm
- 8 Overfitting
- 9 Decision trees
- 10 Decision forests
- 11 Random trees & forests
- 12 Artificial neural networks
Supervised machine learning
- Regression
- Classification
- Parametric
- Instance-based
- Overview: LinReg, KNN, Decision Trees, ANN
How ML fits into the computing at a hedge fund
- Long/short
Time series prediction as an ML problem
[note: need to create fake stock data that has embedded patterns]
Learner APIs
Linear regression
KNN
Assessing a learning algorithm
- Now that we have two, (linreg & KNN), let's compare them
- RMS error
- Scatterplot predict vs actual
- Corrcoef
