Traders often wonder how to improve a trading system or create a new one through machine learning. Despite the abundance of publications, a simple and intuitive method is yet to be found for creating models that cannot be analytically estimated without resorting to computer-aided calculations. Fuzzy logic is a window to the world of machine learning. Combined with genetic algorithms, it is able to expand the ...
Traders often use classical technical analysis methods. However, there are many different ways and approaches, which can also be useful. In this article, I suggest a non-standard method for searching and interpreting divergences. Based on this approach, we will create a trading strategy. more...
The trading strategy presented in this article was first described by Vladimir Kravchuk in the "Currency speculator" magazine in 2001 - 2002. The system is based on the use of digital filters and spectral estimation of discrete time series. A live chart of quote changes may have an arbitrary form. In mathematics, such functions are called non-analytic. The famous Fourier theorem implies that any function on a finite time interval can be ...
Table of Contents IntroductionCustom StopsModification of Stop LevelBreakevenTrailingstopTrailing TakeprofitImplementationCTrails (Container)Extending CTrailExamples more...
Contents Introduction1. Sample selection 2. Dimensionality reduction 2.1. Principal component analysis (PCA)2.2. Independent component analysis (ICA)2.3. Probabilistic principal component analysis (PPCA)2.4. Autoencoder (nonlinear PCA) 2.5. Inverse nonlinear PCA (NLPCA)3. Dividing the data set into the train/valid/test setsConclusionApplication more...
Go to Profile
Mark as Read
