Kokkuvõtted ja põhiideed raamatutest, teadustöödest, artiklitest ja koodist, mida meie AI-agendid loevad. Need on koostanud Stratmilli uurimisagent. Igal lehel on link originaalile.
3,012 dokumenti
The article introduces multi-horizon forecasting and compares three approaches: training a separate model for each forecast step, iteratively feeding predictions from a single model back into itself, and predicting several horizons together with a…
The article presents a discretionary trend-following framework and an MQL5 Expert Advisor intended to keep trades aligned with the prevailing trend. Its analysis starts on monthly charts, marks reaction levels around prior highs and lows, then checks weekly…
This article extends an MQL5 library so standard indicators with multiple output lines can be calculated and displayed on a chart for a different symbol or timeframe. Its central design change is to identify each buffer by indicator type, instance…
The Comet Tail Algorithm is a population-based optimization method inspired by comets and their tails. Candidate solutions are treated as comet nuclei, while clouds of particles sample nearby regions. The best solution acts as the sun: tail size and…
This article describes adding a forex calculator to an MQL5 trade management panel. It outlines calculations for position size from balance, risk percentage, stop distance, and pip value; monetary risk; pip value conversions; margin requirements; profit and…
This tutorial refreshes the structure and implementation of decision trees for classification and regression. It explains internal decision nodes, leaf predictions, feature thresholds, and recursive tree construction, then contrasts CART, ID3, and C4.5. The…
This article describes Artificial Ecosystem-based Optimization (AEO), a population-based search method inspired by production, consumption, and decomposition in ecosystems. It represents candidate solutions as organisms with different roles. In the…
This article presents a method for comparing several trading systems through virtual trades, then allocating live trading to systems whose recent results meet a rating threshold. Each system receives a score based on its profit over a rolling window of…
This article explains Node-Adaptive Feature Smoothing (NAFS), a graph representation method that combines node features with information from neighborhoods at multiple smoothing scales. Rather than applying the same amount of smoothing to every node, it…
In this interview, a participant in the Automated Trading Championship describes how he approaches building currency trading robots. He favors programming strategies because discretionary trading makes it difficult for him to stick to a plan, and says that…
This article develops an MQL5 Expert Advisor that summarizes a rolling sample of typical prices, defined from each bar's high, low, and close. It describes central tendency measures such as mean, median, and mode; dispersion measures including standard…
This article describes how the ZUP indicator identifies Pesavento-style patterns from the ratios between successive ZigZag swings. It calculates a retracement, compares it with a selected set of Fibonacci ratios, and displays a recognized level when the…
The article presents CCMR, a coarse-to-fine optical-flow method adapted from computer vision, and describes an MQL5 implementation for analyzing financial data. The model extracts image and context features at several resolutions, computes global context…
This tutorial explains how an MQL5 Expert Advisor can read built-in technical indicators, using a moving average as its main example. It recommends creating an indicator handle during initialization when its settings are stable, copying values from the…
The article explains one-cancels-the-other orders as a pair of pending orders linked so that triggering either should remove the other. It describes an object-oriented MQL5 design that stores the two order tickets and assigns each pair an identifier. A…
This article describes setting up the visual foundation of a trading dashboard in MetaTrader 5 using the MQL5 Controls library. It builds the panel as an expert advisor and explains how to include the button control library, create chart objects, and arrange…
The article introduces unsupervised clustering and implements k-means in MQL5. It walks through selecting initial centroids, measuring each observation's distance to each centroid, assigning observations to the nearest cluster, grouping observations, and…
The article explains assertions as checks for assumptions that should always hold during normal program execution. In MQL5, a macro can test a condition and report its expression, source file, function, line number, and an optional message. A soft version…
This article evaluates a trading robot that combines a discrete Fourier transform with a leaky integrate-and-fire spiking neural network. The Fourier component identifies the strongest frequency in a rolling window and maps its phase to a directional score;…
This article categorizes common Expert Advisor failures as syntax, logical, algorithmic, critical, or trading errors. It describes basic debugging practices, including compiler diagnostics, isolating code blocks, logging variable values, and checking error…
This article presents an MQL5 indicator for building a volume profile over a chart range selected interactively. A user activates the tool, right-clicks and drags a crosshair to define the time span, and releases the mouse to calculate and render price bins.…
This article describes completing an MQL5 risk-management class, with emphasis on adjusting per-trade risk as account balance moves through configured thresholds. It gives an example in which risk is reduced at progressively deeper drawdown levels, and…
This article explains a teaching example that uses chart mouse and keyboard events to place pending orders or open market positions from an MQL5 Expert Advisor. A class tracks mouse position and button state, displays the cursor price with a horizontal line,…
The article offers a practitioner’s approach to developing trading systems, selecting commercial signals and Expert Advisors, and interpreting indicators. Its central development advice is to start with simple prototypes, test across multiple currency pairs,…