Discussing the article: "Hidden Markov Models in Machine Learning-Based Trading Systems"

[MetaQuotes]

Check out the new article: Hidden Markov Models in Machine Learning-Based Trading Systems.

Hidden Markov Models (HMMs) are a powerful class of probabilistic models designed to analyze sequential data, where observed events depend on some sequence of unobserved (hidden) states that form a Markov process. The main assumptions of HMM include the Markov property for hidden states, meaning that the probability of transition to the next state depends only on the current state, and the independence of observations given knowledge of the current hidden state.

The hmmlearn library is a set of Python algorithms for unsupervised learning (hidden Markov models). It is designed to provide simple and efficient tools for working with HMMs, following the scikit-learn library API, facilitating integration into existing machine learning projects and simplifying the training process for users familiar with scikit-learn. Hmmlearn is built on top of fundamental scientific Python libraries, such as NumPy, SciPy, and Matplotlib.

hmmlearn key capabilities include the implementation of various HMM models with different emission distribution types, training of model parameters from observed data, inferring the most probable hidden state sequences, generating samples from trained models, and the ability to save and load trained models. The variety of implemented models allows users to select the most appropriate emission distribution type depending on the nature of their data. The data type (continuous, discrete, counters) determines which probability distribution best describes the process of generating observations in each hidden state.

Author: dmitrievsky

[fxsaber]

Затем, следует скомпилировать приложенного в конце статьи бота и протестировать его в тестере MetaTrader 5.

Fig. 14. testing of the best model in MetaTrader 5 terminal for the whole period

The MQL5 files.zip archive contains files for the MetaTrader 5 terminal

Please make it a standard to publish the corresponding tst-files of backtest results posted in the articles. Thank you.

[[Deleted]]

fxsaber #:

Please make it standard to publish the corresponding tst-files of the backtest results posted in the articles as well. Thank you.

Unfortunately, I don't write that often. I will try to remember for the future.