Machine Learning for Algorithmic Trading by Stefan Jansen

Author:Stefan Jansen
Language: eng
Format: epub
Tags: COM004000 - COMPUTERS / Intelligence (AI) & Semantics, COM018000 - COMPUTERS / Data Processing, COM044000 - COMPUTERS / Neural Networks
Publisher: Packt
Published: 2020-07-30T12:45:55+00:00

In addition to directly controlling the size of the ensemble, there are various regularization techniques, such as shrinkage, that we encountered in the context of the ridge and lasso linear regression models in Chapter 7, Linear Models – From Risk Factors to Return Forecasts. Furthermore, the randomization techniques used in the context of random forests are also commonly applied to gradient boosting machines.

Ensemble size and early stopping

Each boosting iteration aims to reduce the training loss, increasing the risk of overfitting for a large ensemble. Cross-validation is the best approach to find the optimal ensemble size that minimizes the generalization error.

Since the ensemble size needs to be specified before training, it is useful to monitor the performance on the validation set and abort the training process when, for a given number of iterations, the validation error no longer decreases. This technique is called early stopping and is frequently used for models that require a large number of iterations and are prone to overfitting, including deep neural networks.

Keep in mind that using early stopping with the same validation set for a large number of trials will also lead to overfitting, but just for the particular validation set rather than the training set. It is best to avoid running a large number of experiments when developing a trading strategy as the risk of false discoveries increases significantly. In any case, keep a hold-out test set to obtain an unbiased estimate of the generalization error.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.