Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
3,012 documents
This document describes an MQL5 dashboard that organizes symbols by rows and timeframes by columns, displaying a color-coded score for each combination. The score combines a linear trend slope, price-change momentum, and price volatility using configurable…
This article compares MetaTrader 4 genetic optimization with direct exhaustive search for a MACD-based Expert Advisor whose inputs include stop loss, take profit, trailing stop, and signal filters. It reports three EURUSD hourly tests over a two-year period,…
The document introduces one-dimensional singular spectrum analysis (SSA) as a way to decompose a time series into components such as trend, periodic movement, and noise, then reconstruct selected components and forecast them. Basic SSA embeds the series in a…
This document explains how an MQL5 Expert Advisor can read account and instrument properties needed for money management. Account queries provide balance, equity, used and free margin, floating profit or loss, deposit currency, leverage, Stop Out threshold…
The article explains how relational reinforcement learning can represent objects and events as nodes in a graph, with weighted links expressing their dependencies. It motivates this approach with a channel breakout example: formation, boundary breaks, and…
This article outlines an MQL5 expert advisor that uses a neural network to generate buy or sell signals from moving averages, RSI, and ATR. The network has input, hidden, and output layers, uses sigmoid activation, and is trained through backpropagation. The…
This introductory article uses a small set of plotted points and a linear model to explain how a neural network might fit a mathematical relationship. It first considers a line constrained to pass through the origin, then motivates finding model parameters…
The article presents Exploratory Data for Offline Reinforcement Learning (ExORL), a framework that focuses on how training data is collected rather than proposing a new policy algorithm or network architecture. It outlines three stages: gather unlabeled…
The article describes using archived economic calendar data to build signals for a wizard assembled Expert Advisor. Its example focuses on relative inflation readings for the currencies in GBPUSD, with the aim of using economic releases as a fundamental…
This article extends a MetaTrader 5 analytics Expert Advisor to send periodic market summaries to Telegram. The reported metrics include prior-day prices and volume, current-day volume, support and resistance levels, account balance and equity, spread, lot…
The article explains Distance Weighted Supervised Learning (DWSL), an offline method for learning goal-conditioned policies from state-action trajectories that may be suboptimal and lack explicit goal labels. It learns a distribution of distances between…
This article develops bar-level order-flow measures for M1 futures data, where OHLCV bars do not reveal each trade’s aggressor side. It describes an OHLCV approximation of VPIN based on where a bar closes within its range, signed volume imbalance, relative…
This installment extends an MQL5 trading library so pending requests can wait for user-defined conditions before sending orders. Conditions are stored with their source, property, comparison rule, reference value, and current value. A manager checks them on…
The article shows how to display externally sourced candle data in an MQL5 indicator by reading values previously saved to a file. Its workflow separates data retrieval from visualization: an Expert Advisor can make WebRequest calls and write candle data to…
The article explains how resampling can estimate predictive model performance when a separate validation dataset is unavailable. It defines apparent error on the training data, prediction error for a fitted model on new observations, population error across…
The article explains an evolution strategy for tuning neural network parameters when analytical gradients are unavailable or difficult to calculate. It contrasts the method with genetic algorithms, which select and recombine varied individuals, and estimates…
The article explains Multi-Layer Key-Value sharing (MLKV), a Transformer attention design intended to reduce the memory used by autoregressive decoding’s key-value cache. It places MLKV alongside Multi-Query Attention and Grouped-Query Attention: those…
The article introduces RSA’s public and private keys, modular exponentiation, and the need to encode messages as numbers. It uses a deliberately tiny numerical example to illustrate encryption and decryption, then discusses big integers, key generation,…
The article explains support vector regression’s epsilon-insensitive loss and implements it as a training objective for a multilayer perceptron in MQL5. Prediction errors within an epsilon margin receive no penalty, while larger errors are penalized; a…
This installment develops an options-emulation expert advisor for MetaTrader 5 and adds chart visualization of option levels. It explains how to convert target delta levels into underlying-price levels by searching above or below a strike with the bisection…
The article compares the Hurst exponent with a local fractal index for characterizing financial price series. It describes the Hurst-based relation between persistence and fractal dimension, but notes that reliable estimates generally need long samples and…
The article presents a method for screening closed-position histories for risks that headline win rates, profit factors, and equity curves can hide. It reconstructs positions from CSV rows or account deal history, then scores four features: larger trades…
The article presents entropy as a way to assess how much information an indicator's observed values contain before using them as predictors in machine learning. Because the usual entropy calculation applies to discrete outcomes, it recommends dividing a…
This technical guide explains how MetaTrader custom indicators are configured, displayed, and called by other programs. It describes choosing the main chart or a separate window, setting scale limits, declaring indicator buffers, and assigning colors. An…