All (not yet) about Strategy Tester, Optimization and Cloud - page 11

[Sergey Golubev]

Integrating ML models with the Strategy Tester (Part 3): Managing CSV files (II)

In this article, we will focus on the third part of Strategy Tester integhttps://www.mql5.com/en/articles/12069ration with Python. We will see the creation of the CFileCSV class for the efficient management of CSV files. We will examine some examples and the code, so that the readers better understand how this class can be implemented in practice.

[Sergey Golubev]

The most quick way to download the history of ticks (attach this EA to the chart of MT5 for the history to be downloaded): post #151 - please note that this EA is using MTTester.mqh file from this CodeBase link (the file should be placed to  \MQL5\Include\fxsaber\MultiTester\ )

[Sergey Golubev]

Sergey Golubev #:

Applying the Monte Carlo method for optimizing trading strategies

• General theory
• Probabilistic EA model
• Applying the theory
• Profit robustness against random scatter
• Profit robustness against drawdown
• Profit distribution robustness against price nonstationarity
• Conclusion
• Attached files 

Monte Carlo Permutation Tests in MetaTrader 5

.. in this article we will demonstrate a permutation test involving randomly permuted price data using MetaTrader 5. We will present code for permuting price series , as well as a script that automates the initial steps when preparing to conduct a permutation test of a complete EA.

[Sergey Golubev]

MQL5 Cloud Network and MQL5 VPS in relation to AVX512 and AVX2 - post #74 (all the details - read this page)

[Sergey Golubev]

Sergey Golubev #:

Optimization management (Part I): Creating a GUI 

GUI: Tips and Tricks for creating your own Graphic Library in MQL

Developing a GUI library is one of the biggest non-specific projects that anyone could think of in the context of MetaTrader 5, aside from very advanced things like AI, (good) neural networks and... getting fluent in using a GUI library that you haven't developed.

In this article our goal isn't to teach you how to make an interface or show the steps to develop a fully functional library. Instead, we will provide examples how some specific pieces of GUI libraries can be made, so that they can serve as a starting point to make one, to solve a specific issue that you may have found or to get an initial understanding about is even happening inside of some huge codebase for an already complete GUI library.

[Sergey Golubev]

Estimate future performance with confidence intervals

Creation of profitable automated trading systems is no easy task. Even if one happens to make a profitable expert advisor, there are still questions about whether it is worth the risk. We may be satisfied that our strategy will not blow through all capital allocated to it, but this is no  reason to immediately enable live trading. Ultimately, profit is the motive and if we later find that our strategy is indeed profitable, but not profitable enough to justify the risk, or generates poor returns relative to other investment opportunities we will no doubt have serious regrets.

Therefore, in this article we will explore techniques borrowed from the field of statistics that can help us estimate the future performance of an automated trading system, using data collected from out of sample tests.

[Sergey Golubev]

Developing a quality factor for Expert Advisors

In this article, we will see how to develop a quality score that your Expert Advisor can display in the strategy tester.

[Sergey Golubev]

• New trading account report - the announcement;
  more -
  
• Trading report export and new machine learning methods in MQL5 - the announcement

[Sergey Golubev]

Population optimization algorithms: Shuffled Frog-Leaping algorithm (SFL)

1. Introduction
2. Algorithm
3. Test results

The Shuffled Frog Leaping Algorithm (SFL) was proposed by М. Eusuff and other authors in 2003. This algorithm combines the principles of the memetic algorithm and the particle swarm algorithm, and its design was inspired by the behavior of a group of frogs during the foraging process.

[Sergey Golubev]

Population optimization algorithms: Mind Evolutionary Computation (MEC) algorithm

Evolutionary computation is a subfield of computational intelligence, machine learning and artificial intelligence. It is widely used in optimization problems, robot design, creating decision trees, tuning data analysis algorithms, training neural networks and tuning hyperparameters. Instead of using classical numerical methods, evolutionary computing uses inspiration from biological evolution to develop good solutions. They are especially useful when there is no known derivative of the fitness function or when the fitness function has many local extrema that can hamper sequential methods.

MEC algorithms implement the presented concept using local competition and dissimilation operations responsible for local and global search, respectively. Message boards are used by the algorithm to store information about the evolutionary history of the population. The optimization process is controlled based on this information.