Add a new article
Neural networks made easy (Part 37): Sparse Attention
Neural networks made easy (Part 37): Sparse Attention
In the previous article, we discussed relational models which use attention mechanisms in their architecture. One of the specific features of these models is the intensive utilization of computing resources. In this article, we will consider one of the mechanisms for reducing the number of computational operations inside the Self-Attention block. This will increase the general performance of the model.
Understanding order placement in MQL5
Understanding order placement in MQL5
When creating any trading system, there is a task we need to deal with effectively. This task is order placement or to let the created trading system deal with orders automatically because it is crucial in any trading system. So, you will find in this article most of the topics that you need to understand about this task to create your trading system in terms of order placement effectively.
Wrapping ONNX models in classes
Wrapping ONNX models in classes
Object-oriented programming enables creation of a more compact code that is easy to read and modify. Here we will have a look at the example for three ONNX models.
Simple Mean Reversion Trading Strategy
Simple Mean Reversion Trading Strategy
Mean reversion is a type of contrarian trading where the trader expects the price to return to some form of equilibrium which is generally measured by a mean or another central tendency statistic.
Revisiting an Old Trend Trading Strategy: Two Stochastic oscillators, a MA and Fibonacci
Revisiting an Old Trend Trading Strategy: Two Stochastic oscillators, a MA and Fibonacci
Old trading strategies. This article presents one of the strategies used to follow the trend in a purely technical way. The strategy is purely technical and uses a few technical indicators and tools to deliver signals and targets. The components of the strategy are as follows: A 14-period stochastic oscillator. A 5-period stochastic oscillator. A 200-period moving average. A Fibonacci projection tool (for target setting).
Can Heiken-Ashi Combined With Moving Averages Provide Good Signals Together?
Can Heiken-Ashi Combined With Moving Averages Provide Good Signals Together?
Combinations of strategies may offer better opportunities. We can combine indicators or patterns together, or even better, indicators with patterns, so that we get an extra confirmation factor. Moving averages help us confirm and ride the trend. They are the most known technical indicators and this is because of their simplicity and their proven track record of adding value to analyses.
Category Theory in MQL5 (Part 12): Orders
Category Theory in MQL5 (Part 12): Orders
This article which is part of a series that follows Category Theory implementation of Graphs in MQL5, delves in Orders. We examine how concepts of Order-Theory can support monoid sets in informing trade decisions by considering two major ordering types.
Category Theory in MQL5 (Part 11): Graphs
Category Theory in MQL5 (Part 11): Graphs
This article is a continuation in a series that look at Category Theory implementation in MQL5. In here we examine how Graph-Theory could be integrated with monoids and other data structures when developing a close-out strategy to a trading system.
Other classes in DoEasy library (Part 67): Chart object class
Other classes in DoEasy library (Part 67): Chart object class
In this article, I will create the chart object class (of a single trading instrument chart) and improve the collection class of MQL5 signal objects so that each signal object stored in the collection updates all its parameters when updating the list.
Category Theory in MQL5 (Part 10): Monoid Groups
Category Theory in MQL5 (Part 10): Monoid Groups
This article continues the series on category theory implementation in MQL5. Here we look at monoid-groups as a means normalising monoid sets making them more comparable across a wider span of monoid sets and data types..
Prices in DoEasy library (part 61): Collection of symbol tick series
Prices in DoEasy library (part 61): Collection of symbol tick series
Since a program may use different symbols in its work, a separate list should be created for each of them. In this article, I will combine such lists into a tick data collection. In fact, this will be a regular list based on the class of dynamic array of pointers to instances of CObject class and its descendants of the Standard library.
Multilayer perceptron and backpropagation algorithm (Part 3): Integration with the Strategy Tester - Overview (I).
Multilayer perceptron and backpropagation algorithm (Part 3): Integration with the Strategy Tester - Overview (I).
The multilayer perceptron is an evolution of the simple perceptron which can solve non-linear separable problems. Together with the backpropagation algorithm, this neural network can be effectively trained. In Part 3 of the Multilayer Perceptron and Backpropagation series, we'll see how to integrate this technique into the Strategy Tester. This integration will allow the use of complex data analysis aimed at making better decisions to optimize your trading strategies. In this article, we will discuss the advantages and problems of this technique.
Timeseries in DoEasy library (part 57): Indicator buffer data object
Timeseries in DoEasy library (part 57): Indicator buffer data object
In the article, develop an object which will contain all data of one buffer for one indicator. Such objects will be necessary for storing serial data of indicator buffers. With their help, it will be possible to sort and compare buffer data of any indicators, as well as other similar data with each other.
Category Theory in MQL5 (Part 7): Multi, Relative and Indexed Domains
Category Theory in MQL5 (Part 7): Multi, Relative and Indexed Domains
Category Theory is a diverse and expanding branch of Mathematics which is only recently getting some coverage in the MQL5 community. These series of articles look to explore and examine some of its concepts & axioms with the overall goal of establishing an open library that provides insight while also hopefully furthering the use of this remarkable field in Traders' strategy development.
Timeseries in DoEasy library (part 54): Descendant classes of abstract base indicator
Timeseries in DoEasy library (part 54): Descendant classes of abstract base indicator
The article considers creation of classes of descendant objects of base abstract indicator. Such objects will provide access to features of creating indicator EAs, collecting and getting data value statistics of various indicators and prices. Also, create indicator object collection from which getting access to properties and data of each indicator created in the program will be possible.
Category Theory in MQL5 (Part 6): Monomorphic Pull-Backs and Epimorphic Push-Outs
Category Theory in MQL5 (Part 6): Monomorphic Pull-Backs and Epimorphic Push-Outs
Category Theory is a diverse and expanding branch of Mathematics which is only recently getting some coverage in the MQL5 community. These series of articles look to explore and examine some of its concepts & axioms with the overall goal of establishing an open library that provides insight while also hopefully furthering the use of this remarkable field in Traders' strategy development.
Creating an EA that works automatically (Part 12): Automation (IV)
Creating an EA that works automatically (Part 12): Automation (IV)
If you think automated systems are simple, then you probably don't fully understand what it takes to create them. In this article, we will talk about the problem that kills a lot of Expert Advisors. The indiscriminate triggering of orders is a possible solution to this problem.
Creating an EA that works automatically (Part 10): Automation (II)
Creating an EA that works automatically (Part 10): Automation (II)
Automation means nothing if you cannot control its schedule. No worker can be efficient working 24 hours a day. However, many believe that an automated system should operate 24 hours a day. But it is always good to have means to set a working time range for the EA. In this article, we will consider how to properly set such a time range.
Creating an EA that works automatically (Part 09): Automation (I)
Creating an EA that works automatically (Part 09): Automation (I)
Although the creation of an automated EA is not a very difficult task, however, many mistakes can be made without the necessary knowledge. In this article, we will look at how to build the first level of automation, which consists in creating a trigger to activate breakeven and a trailing stop level.
Experiments with neural networks (Part 4): Templates
Experiments with neural networks (Part 4): Templates
In this article, I will use experimentation and non-standard approaches to develop a profitable trading system and check whether neural networks can be of any help for traders. MetaTrader 5 as a self-sufficient tool for using neural networks in trading. Simple explanation.
Neural networks made easy (Part 34): Fully Parameterized Quantile Function
Neural networks made easy (Part 34): Fully Parameterized Quantile Function
We continue studying distributed Q-learning algorithms. In previous articles, we have considered distributed and quantile Q-learning algorithms. In the first algorithm, we trained the probabilities of given ranges of values. In the second algorithm, we trained ranges with a given probability. In both of them, we used a priori knowledge of one distribution and trained another one. In this article, we will consider an algorithm which allows the model to train for both distributions.
Neural networks made easy (Part 36): Relational Reinforcement Learning
Neural networks made easy (Part 36): Relational Reinforcement Learning
In the reinforcement learning models we discussed in previous article, we used various variants of convolutional networks that are able to identify various objects in the original data. The main advantage of convolutional networks is the ability to identify objects regardless of their location. At the same time, convolutional networks do not always perform well when there are various deformations of objects and noise. These are the issues which the relational model can solve.
Neural networks made easy (Part 35): Intrinsic Curiosity Module
Neural networks made easy (Part 35): Intrinsic Curiosity Module
We continue to study reinforcement learning algorithms. All the algorithms we have considered so far required the creation of a reward policy to enable the agent to evaluate each of its actions at each transition from one system state to another. However, this approach is rather artificial. In practice, there is some time lag between an action and a reward. In this article, we will get acquainted with a model training algorithm which can work with various time delays from the action to the reward.
Creating an EA that works automatically (Part 07): Account types (II)
Creating an EA that works automatically (Part 07): Account types (II)
Today we'll see how to create an Expert Advisor that simply and safely works in automatic mode. The trader should always be aware of what the automatic EA is doing, so that if it "goes off the rails", the trader could remove it from the chart as soon as possible and take control of the situation.