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 studies stacking as a way to combine predictions from an ensemble of extreme learning machine classifiers. The base models produce outputs on separate training and evaluation samples; those outputs become features for a second-level combiner.…
This article explains how MetaTrader 5 exposes exchange order book data and how to build a reusable MQL5 class to simplify access. It describes subscribing to book-change events for selected symbols, retrieving second-level quotes, and organizing price…
This tutorial outlines how to connect an MQL5 Expert Advisor to a Telegram bot so the terminal can send trading notifications. It describes creating a bot, retrieving its API token, obtaining a chat identifier from an update, and allowing Telegram's API…
In this championship interview, Andrey Voitenko describes an Expert Advisor that trades breaks from a horizontal price channel. It calculates channel boundaries from highs and lows over five minute bars, then places pending orders at the boundaries after…
This article explains Supported Policy Optimization (SPOT), an offline reinforcement learning method intended to reduce unreliable value estimates when a learned policy chooses actions that are poorly represented in its fixed training data. SPOT estimates…
The article tests how often markets qualify as trending versus flat by comparing five classification methods: ADX above a threshold, a Bollinger based trend indicator, Percentage of Trend, an RSI filter, and a ZigZag trend detector. It describes an MQL5 tool…
The article presents a workflow for preparing labeled market time series and training an N-HiTS forecasting model with PyTorch Lightning and PyTorch Forecasting. It retrieves M15 price data through MetaTrader 5, converts it to a dataframe, and adds time and…
The article explains how Renko charts represent price movement with fixed-size bricks while omitting regular time spacing. It outlines construction from a selected timeframe and box size, typically using closing prices: a new brick appears after price…
The article explains ridge regression as a way to estimate linear model coefficients when predictors are correlated. It frames regularization as a bias–variance tradeoff: accepting some bias can reduce variance and overfitting. It also contrasts ridge with…
The article applies Gaussian Naïve Bayes to classify whether a bar closes above or below its open, using Bulls Power, Bears Power, RSI, tick volume, and Money Flow Index as features. It explains preparing a labeled matrix, splitting observations into…
The article turns topological features of a rolling price window into chart and Expert Advisor buffers. It defines persistence entropy separately for H0 connected-component bars and H1 loop bars: entropy is low when persistence is concentrated in a few…
This installment in a logging-library series describes changes intended to make file logging more flexible and efficient. It moves formatting responsibility from a single shared formatter to each handler, allowing destinations such as a console and a file to…
The article explains when MQL5 class objects are constructed and destroyed, covering global variables, local variables, and dynamically allocated objects. Global objects initialize in declaration order and are destroyed in reverse; local objects are created…
This article describes an infrastructure layer that lets an Expert Advisor request logical instrument names while resolving broker-specific symbol variants at runtime. Its components include a persistent mapping store, a resolver, an in-memory cache, and a…
The article proposes a way to test whether price repeatedly reacts at retracement ratios between or beyond standard Fibonacci levels. It describes collecting historical OHLCV data, treating each bar’s high-low range as a candidate swing, filtering out ranges…
This article shows how to build a MetaTrader 5 indicator that displays several timeframe charts inside a chart subwindow. Buttons let users add chart objects for selected timeframes and toggle chart properties, including settings that are unavailable through…
The article compares ten rule-based approaches to trading range-bound markets. Their common structure is to use an indicator channel to mark a presumed sideways range, enter when price reaches an outer boundary, and aim to exit near the opposite boundary. A…
The article outlines an MQL5 mean-reversion strategy that calculates rolling price statistics, including mean, variance, skewness, kurtosis, and the Jarque-Bera statistic. It looks for price moves beyond confidence intervals, using skewness thresholds and a…
The article turns rough-volatility theory into a rolling local Hurst estimate for an XAUUSD intraday trading system. It blocks short-horizon returns into realized-variance observations, takes their logarithms, and estimates roughness from the slope of log…
The article considers which data sources might help a multilayer perceptron forecast the next quarter’s direction for the SPDR XLV healthcare ETF. Candidate inputs include historical OHLC changes, volatility, volume, insurance claims, pharmaceutical sales,…
The article explains genetic algorithms as gradient-free methods for optimizing parametric models, including neural trading models that are not differentiable or are difficult to train with gradient descent. It describes evolving a population of agents…
This article explains how a Virtual Order Manager (VOM) can preserve order-centric behavior in MetaTrader 5, where multiple trades on one symbol may be combined into a single position. It targets setups where several Expert Advisors, or a complex EA, need to…
This article describes Biogeography-Based Optimization (BBO), a population-based method in which each candidate solution is modeled as a habitat and its quality as habitat suitability. Better solutions have higher emigration rates and can share selected…
This article presents reusable MQL5 checks intended to catch invalid trading requests before they reach the broker. It covers validating and normalizing lot sizes against symbol minimums, maximums, and volume steps; checking stop-loss and take-profit…