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...
Table of Contents IntroductionThe differences between the Pennant and the TriangleHorizontal PatternContracting TriangleExpanding TriangleA universal indicator to search for the Horizontal Pattern and TrianglesA universal indicator to search for the Flag, the Pennant and the WedgeTester IndicatorConclusionAttachments more...
Contents Introduction1. Creating features 1.1. Feature transformation 1.1.1. Transformation1.1.2. Normalization1.1.3. Discretization1.2. Creating new features2. Choosing predictors 2.1. Visual evaluation2.2. Analytical evaluation2.3. Neural networkConclusionApplication more...
Algorithmic trading consists not only of planning and development of trading robots but also (to a greater extent) testing and verifying the survivability of ideas and algorithms implemented in them. MetaTrader 5 provides the built-in tester for optimizing Expert Advisors on historical data. This tool is often indispensable in everyday activity. However, its main issue is the search for parameters that remain steadily profitable over time ...
In this article we will continue exploring deep neural networks (DNN) which I started in the previous articles (1, 2, 3).DNN are widely used and intensely developed in many areas. The most common examples of everyday use of neural networks are speech and image recognition and automatic translation from one language into another. DNN are also used in trading. Given the fast development of algorithmic trading, in-depth studying of DNN seems to be useful. ...
Recent Comments