Gang Wu / Profile

The article describes the method of creating a tool for comfortable scalping. However, such an approach to trade opening can be applied in any trading.

This article shows you how to easily use Neural Networks in your MQL4 code taking advantage of best freely available artificial neural network library (FANN) employing multiple neural networks in your code.

This article is a continuation of previous articles on deep neural network and predictor selection. Here we will cover features of a neural network initiated by Stacked RBM, and its implementation in the "darch" package.

The article explores the advantages and disadvantages of trading in flat periods. The ten strategies created and tested within this article are based on the tracking of price movements inside a channel. Each strategy is provided with a filtering mechanism, which is aimed at avoiding false market entry signals.

We continue to build ensembles. This time, the bagging ensemble created earlier will be supplemented with a trainable combiner — a deep neural network. One neural network combines the 7 best ensemble outputs after pruning. The second one takes all 500 outputs of the ensemble as input, prunes and combines them. The neural networks will be built using the keras/TensorFlow package for Python. The features of the package will be briefly considered. Testing will be performed and the classification quality of bagging and stacking ensembles will be compared.

This article describes techniques of operating with Kohonen maps. The subject will be of interest to both market researchers with basic level of programing in MQL4 and MQL5 and experienced programmers that face difficulties with connecting Kohonen maps to their projects.

The present article develops the idea of using Kohonen Maps in MetaTrader 5, covered in some previous publications. The improved and enhanced classes provide tools to solve application tasks.

In this article the author talks about evolutionary calculations with the use of a personally developed genetic algorithm. He demonstrates the functioning of the algorithm, using examples, and provides practical recommendations for its usage.

This article introduces a class designed to give a quick preliminary estimate of characteristics of various time series. As this takes place, statistical parameters and autocorrelation function are estimated, a spectral estimation of time series is carried out and a histogram is built.

One of the most interesting aspects of Self-Organizing Feature Maps (Kohonen maps) is that they learn to classify data without supervision. In its basic form it produces a similarity map of input data (clustering). The SOM maps can be used for classification and visualizing of high-dimensional data. In this article we will consider several simple applications of Kohonen maps.

The purpose of this article is to create the most simple trading strategy that implements the "All or Nothing" gaming principle. We don't want to create a profitable Expert Advisor - the goal is to increase the initial deposit several times with the highest possible probability. Is it possible to hit the jackpot on ForEx or lose everything without knowing anything about technical analysis and without using any indicators?

This article is dedicated to a new and perspective direction in machine learning - deep learning or, to be precise, deep neural networks. This is a brief review of second generation neural networks, the architecture of their connections and main types, methods and rules of learning and their main disadvantages followed by the history of the third generation neural network development, their main types, peculiarities and training methods. Conducted are practical experiments on building and training a deep neural network initiated by the weights of a stacked autoencoder with real data. All the stages from selecting input data to metric derivation are discussed in detail. The last part of the article contains a software implementation of a deep neural network in an Expert Advisor with a built-in indicator based on MQL4/R.

This article covers the main principles set fourth in evolutionary algorithms, their variety and features. We will conduct an experiment with a simple Expert Advisor used as an example to show how our trading system benefits from optimization. We will consider software programs that implement genetic, evolutionary and other types of optimization, and provide examples of application when optimizing a predictor set and parameters of the trading system.

Is it possible to develop an Expert Advisor able to optimize position open and close conditions at regular intervals according to the code commands? What happens if we implement a neural network (multilayer perceptron) in the form of a module to analyze history and provide strategy? We can make the EA optimize a neural network monthly (weekly, daily or hourly) and continue its work afterwards. Thus, we can develop a self-optimizing EA.

The article features formalized rules of two trading strategies 'Turtle Soup' and 'Turtle Soup Plus One' from Street Smarts: High Probability Short-Term Trading Strategies by Linda Bradford Raschke and Laurence A. Connors. The strategies described in the book are quite popular. But it is important to understand that the authors have developed them based on the 15...20 year old market behavior.

The article describes the development of tools (indicator and Expert Advisor) for analyzing the '80-20' trading strategy. The trading strategy rules are taken from the work "Street Smarts. High Probability Short-Term Trading Strategies" by Linda Raschke and Laurence Connors. We are going to formalize the strategy rules using the MQL5 language and test the strategy-based indicator and EA on the recent market history.

The article provides a brief overview of ten trend following strategies, as well as their testing results and comparative analysis. Based on the obtained results, we draw a general conclusion about the appropriateness, advantages and disadvantages of trend following trading.

The article provides the analysis of the following patterns: Flag, Pennant, Wedge, Rectangle, Contracting Triangle, Expanding Triangle. In addition to analyzing their similarities and differences, we will create indicators for detecting these patterns on the chart, as well as a tester indicator for the fast evaluation of their effectiveness.

This article is a continuation of the series of articles about deep neural networks. Here we will consider selecting samples (removing noise), reducing the dimensionality of input data and dividing the data set into the train/val/test sets during data preparation for training the neural network.

This article considers new capabilities of the darch package (v.0.12.0). It contains a description of training of a deep neural networks with different data types, different structure and training sequence. Training results are included.