Machine Learning Tour by Gabriel Moncarz
Version 2.0.0
ML Tour
LinkedIn
Mail
Random Forest - Historical window lenght - 1 day horizon period
Optimizing the historical window lenght for 1 day horizon prediction.
Jupyter notebook
Last updated on 9 Aug 2019
Published on 9 Aug 2019
Edit on GitHub
Prev - Random Forest - Training parameter tunning
Next - Random Forest - Historical window lenght - 2 weeks horizon period
Home
Data Preparation
Linear Regression
Introduction
Look Ahead Bias
Avoiding look ahead bias
Running regression models
Adding historical variables
Ridge, Lasso and ElasticNet
Logistic Regression
Introduction
Running logistic models
Adding historical variables
Logistic training parameters part I
Logistic training parameters part II
Logistic training parameters part III
Strategy parameters
Support Vector Machines - SVM
SVM Regressor
SVM Regressor - Introduction
SVM Regressor - Adding historical variables
SVM Regressor - Data Standardization/normalization
SVM Regressor - Kernels
SVM Regressor - Kernel parameters tunning
SVM Regressor - Historical window lenght
SVM Classifier
SVM Classifier - Introduction
SVM Classifier - Improving the model
SVM Classifier - Historical variables and data normalization
SVM Classifier - Kernels
Decision Trees
Decision Tree Regressor
Decision Trees - Introduction
Decision Trees - Adding historical data
Decision Trees - Training parameter tunning
Decision Trees - Historical window lenght
Decision Trees - Model visualization
Random Forest
Random Forest Regressor
Random Forest Regressor - Introduction
Random Forest Regressor - Adding historical variables
Random Forest - Training parameter tunning
Random Forest - Historical window lenght - 1 day horizon period
Random Forest - Historical window lenght - 2 weeks horizon period
Gradient Boosting Machines - GBM
Gradient Boosting Machine Regressor
Deep Learning
Deep Neural Networks (DNN)
Deep Neural Networks (DNN) Regressor
DNN Regressor - Deep Neural Network Template
DNN Regressor - Basic DNN model
DNN Regressor - Data standardization, normalization and loss optimizers
DNN Regressor - Regularization terms and batch normalization
Convolutional Neural Network (CNN)
Deep Convolutional Neural Networks (CNN) Regressor
CNN Regressor - Sequence Modeling
CNN Regressor Model
Deep Recurrent Neural Network (RNN)
Deep Recurrent Neural Networks (RNN) Regressor
RNN Regressor - Introduction
RNN Regressor - Deep RNN (DRNN)
RNN Regressor - Deep Secuential RNN (DSRNN)
RNN Regressor - Deep Secuential Bidirectional RNN (DSBRNN)
Long Short Term Memory Neural Networks (LSTM)
LSTM Regressor
LSTM Regressor - LSTM Introduction
LSTM Regressor - Deep LSTM (D-LSTM)
LSTM Regressor - Deep Secuential LSTM (DS-LSTM)
LSTM Regressor - Deep Secuential Bidirectional LSTM (DSB-LSTM)
Deep Convolutional Recurrent Neural Network
Deep Convolutional Recurrent Neural Network Regressor
CNN + RNN + DNN
CNN + LSTM + DNN
Reinforcement Learning
Environment
Training a basic RL - DQN model
Building a reinforcement learning micro framework
RL DQN model
RL Dueling DQN
RL DQN with Prioritized Experience Replay
RL DQN with custom policy for regulartization terms
DQN based backtests
Backtest with 5 vars (OLHCV quotes) and custom policy L1/L2 regularization terms
Backtest with 53 inputs and custom policy L1/L2 regularization terms
More Models