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
This article explains why recurrent networks may suit market time series: they carry a hidden state forward, allowing information from earlier observations to influence later processing without repeatedly supplying a large fixed input window. It describes an…
The article explains how discriminant analysis can classify market observations into groups such as upward and downward price moves. It illustrates the idea with technical indicators: statistical analysis can identify variables that contribute little to…
The Grey Wolf Optimizer is presented as a population-based stochastic method for optimizing a fitness function. Candidate solutions are ranked as alpha, beta, and delta leaders, while the remaining candidates update their positions using those leaders. A…
The article concludes an implementation series on the SAGDFN adaptive graph forecasting framework, focusing on its OneStepFastGConv component. The framework constructs a sparse graph by selecting significant neighbors, then applies sparse multi-head…
The article explains how MetaTrader 5 custom symbols can store user-defined tick histories, contract properties, and price bars for Strategy Tester use. Traders can build synthetic instruments and non-time-based charts, including Renko, Range, and…
This article describes an MQL5 Expert Advisor that turns swing highs, swing lows, and pullback logic into multi-timeframe reversal trades. It tracks recent and prior swing points on higher and lower timeframes, assigns bullish, bearish, or neutral structure…
The article evaluates whether the CBOE Euro and Gold volatility indexes (EVZ and GVZ) add forecasting value for XAUEUR. It describes merging the indexes with daily XAUEUR OHLC data, imputing missing values with column means, and examining correlations,…
The article describes an automated forex system that builds a matrix of exchange rates for eight major currencies and estimates pairwise fair values from direct quotes and cross rates. It uses currency transitivity—for example, deriving one cross rate…
The article examines how trading activity varies across intraday sessions and argues that fixed-time bars can make indicator observations statistically uneven. It proposes operational time, measured by a fixed number of ticks per bar, as a way to normalize…
This tutorial explains how to use MetaEditor’s debugger to find errors in MQL5 indicators and Expert Advisors. It demonstrates a rolling z-score indicator with two planted defects: an off-by-one loop that can read outside its intended window, and a variance…
The article addresses weaknesses in randomly sampled training labels for a market classifier, including class imbalance, serial dependence among examples, and overlap between classes. It uses principal component analysis to visualize feature structure and…
This article explains how to plan the second and third stages of an automated optimization pipeline for a multi-currency Expert Advisor. The pipeline stores optimization tasks for sequential execution in the Strategy Tester. In the second stage, parameter…
The article describes the Shuffled Frog-Leaping algorithm, a population-based optimization method inspired by memetic search and particle swarm optimization. Candidate solutions, represented as frogs, are divided among memeplexes. Within each group,…
The article explains how to design, generate, and handle custom chart events in MQL5 Expert Advisors. It proposes classifying events by source, including indicator signals, order or position changes, and external inputs such as a manual trading toggle. It…
The article presents a discretionary and automated approach to fair value gaps (FVGs), treating them as price areas left by rapid directional moves. It proposes mapping gaps from higher to lower timeframes, establishing trend bias with price structure and…
This article combines a multifractal model of asset returns into a MetaTrader 5 library with a single facade. Its Fit stage first performs partition analysis to estimate scaling behavior, including the Hurst exponent and multifractality diagnostics, then…
The article explains Singular Spectrum Analysis (SSA) as a non-parametric way to separate a time series into estimated trend, periodic components, and residual noise. It describes embedding observations into a trajectory matrix using a chosen window length,…
The article presents an MQL5 dashboard that evaluates closed trading history using expectancy and a Trade Quality Score. Its motivation is that win rate alone can mislead: it ignores the relative size of wins and losses, and an identical rate carries…
The article introduces principal component analysis as a way to reduce the dimensions of data while retaining directions that explain much of its variance. It reviews eigenvectors and eigenvalues, compares PCA with singular value decomposition and power…
This article introduces request authentication for exchange APIs from MQL5, focusing on signatures, message authentication codes, HMAC, and SHA-256. It explains how a client combines request data with a secret key to generate a signature that a server can…
The article explains number walls, a matrix method for examining sequences and deriving recurrence relations. Repeated application of a cross rule fills the matrix; rows of zeros indicate that a sequence can be represented by a finite relation among earlier…
The article explains least-squares support-vector machines for time-series regression and describes how lagged observations form predictor vectors for forecasting. LS-SVM replaces a constrained nonlinear optimization with a linear system whose kernel matrix…
The article translates fixed-width fractional differentiation from Python into an MQL5 engine and custom indicator for live market data. It explains how to generate weights recursively until they fall below a chosen threshold, reverse them to align with the…
The article introduces chronological validation for machine-learning models in trading and explains why ordinary shuffled cross-validation can leak future information into training. It outlines a workflow using historical EUR/USD data: create differenced…