Multicurrency monitoring of trading signals (Part 4): Enhancing functionality and improving the signal search system
Quote:
In the third part, we have created a basic system for searching signals, which however was based on a small set of indicators and a simple set of search rules. Also, I received suggestions for usability improvements which could be made in the visual part of the trade monitor. This is what we are going to implement in this part.
Contents
more...
----------------
- Multicurrency monitoring of trading signals (Part 1): Developing the application structure
- Multicurrency monitoring of trading signals (Part 2): Implementation of the visual part of the application
- Multicurrency monitoring of trading signals (Part 3): Introducing search algorithms
Developing a cross-platform grid EA: testing a multi-currency EA
Quote:
This article is a kind of postscript for a series of articles devoted to grid Expert Advisors:
more...
Native Twitter Client for MT4 and MT5 without DLL
Quote:
Tweeter provides free platform for anyone to post anything on their site. It can be as valuable as financial tips or as valueless as any prominent person can be in expressing her/his thoughts. Since this article primary focus on the media instead of its contents, let's get started.
For those who can code in other programming languages might find these Twitter Libraries are useful for reference. They are great ressources that provide great insight into implementation details which are sometime not obvious from simply reading API documentation only.
more...
1 Attachment(s)
Practical application of neural networks in trading
Attachment 40612
Quote:
This article considers the application of neural networks when creating trading robots. This is the narrow sense of this problem. More broadly, we will try to answer some questions and to address several problems:
- Can a profitable system be created using machine learning?
- What can a neural network give us?
- The rationale for training neural networks for decision making.
- Neural Network: is it difficult or simple?
- How to integrate a neural network into a trading terminal?
- How to test a neural network? Testing stages.
- About training samples.
more...
1 Attachment(s)
Quick Manual Trading Toolkit: Basic Functionality
Calculating mathematical expressions (Part 2). Pratt and shunting yard parsers
Quote:
In this article, we continue to study various mathematical expression parsing methods and their implementation in the MQL language. In the
first part we considered recursive descent parsers. The main advantage of such parsers is their user-friendly structure, which is directly related to specific grammar of expressions. But when it comes to efficiency and technical features, there are other types of parsers that are worth paying attention to.
more...
1 Attachment(s)
Quick Manual Trading Toolkit: Working with open positions and pending orders
Attachment 40827
Contents
Quote:
We have previously created the basic functionality, which is designed to assist the traders who prefer manual trading. We mainly focused on convenient work related to order placing, and thus most of the functions were related to market entries. However, any trading strategy, whether it be manual or automatic, should have three main stages when working with the markets. These include market entry rules, open position management and closing conditions. As for now, the toolkit only covers the first stage. Therefore, as further development, we can add more opportunities for working with open positions or pending order, and to expand conditions for closing deals. All calculation should be performed by the toolkit, while the decision should be made by the trader.
more...
1 Attachment(s)
A system of voice notifications for trade events and signals
1 Attachment(s)
Gradient Boosting (CatBoost) in the development of trading systems. A naive approach
Attachment 41033
Quote:
Gradient boosting is a powerful machine learning algorithm. The method produces an ensemble of weak models (for example, decision trees), in which (in contrast to
bagging) models are built sequentially, rather than independently (in parallel). This means that the next tree learns from the mistakes of the previous one, then this process is repeated, increasing the number of weak models. This builds a strong model which can generalize using heterogeneous data. In this experiment, I used the
CatBoost library developed by Yandex. It is one of the most popular libraries, along with XGboost and LightGBM.
The purpose of the article is to demonstrate the creation of a model based on machine learning. The creation process consists of the following steps:
- receive and preprocess data
- train the model using the prepared data
- test the model in a custom strategy tester
- port the model to MetaTrader 5
The Python language and the MetaTrader 5 library are used for preparing the data and for training the model.
more...