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.
2,013 documents
This installment outlines a transition from embedding a multi-currency Expert Advisor’s strategy configuration in an initialization string to storing individual strategy instances in a separate database. The broader optimization workflow produces optimized…
In this interview, an experienced Expert Advisor developer discusses why he builds systems that trade several currency pairs, and how their components can be organized. He contrasts a central controller that limits trading on poorly performing pairs with…
The article addresses parameter overfitting by proposing that a trading system be optimized across multiple instruments with one shared parameter set. The rationale is that testing across different price behaviors and repeated patterns may provide a more…
This tutorial describes a reusable MQL class for HTTP communication through WinInet. It outlines the lifecycle of a network session and connection, sending requests, reading server responses, and closing handles. The examples cover retrieving page contents…
The article explains how an exponentially weighted covariance matrix can help a multi-symbol trading system react faster to changing correlations than a fixed rolling window. Each update blends the prior covariance estimate with the latest return…
The article presents an MQL5 architecture for coordinating multiple symbol-specific trading agents through a central Portfolio Controller. The controller tracks shared exposure, publishes risk limits and halt state, and applies portfolio-level safeguards;…
This article extends an MQL5 system for displaying multiple indicators or symbols in chart subwindows. It explains how a class stores chart-object details in a structure and parses optional syntax for setting an indicator’s timeframe and pixel width. A fixed…
This final article in a series explains how MQTT publish/subscribe messaging can move live quotes between MetaTrader 5 accounts when a trading account lacks a symbol available from a separate data provider. A publishing service reads quotes on the source…
The article presents a Sentiment Tilt Meter that turns recent candle behavior into a smoothed score from negative to positive, combining configurable timeframes into one view. Its candle-level inputs include body size relative to range, close location within…
This article outlines a proposed trading system that represents instruments and market variables as a network, applies causal discovery, and uses a Vector Autoregression model to forecast multiple related time series. It describes FCI as the causal discovery…
This installment extends a portfolio-risk analysis by turning a covariance matrix into an inspectable object. It describes calculating logarithmic returns from closing prices, arranging assets as rows and observations as columns, and using MQL5’s covariance…
The article explains CATCH, a neural network framework for detecting anomalies in multivariate market time series. It transforms normalized data with an FFT, divides the real and imaginary spectra into patches, and uses a channel-masked Transformer to learn…
The article explains GinAR, an end-to-end neural architecture for forecasting multivariate time series when some variables have incomplete or entirely missing histories. It combines a simple recurrent unit with Interpolation Attention, which reconstructs…
The article describes an MQL5 expert advisor that manages trades across 30 forex and metal symbols from one chart. Traders can select which pairs to trade, add broker-specific symbol prefixes or suffixes, and restrict activity to a chosen trading session.…
The document introduces Joint Recurrence Quantification Analysis (JRQA) as a way to examine whether two time series revisit their own past states at the same time indices. It distinguishes this from cross-recurrence analysis, which compares states across the…
The document explains two common risks in multi-timeframe MQL5 systems: indicator handles that are poorly managed and signals based on values from a still-forming bar. It recommends creating handles during initialization, reusing them, reading the last…
This article describes a cross-market trend-following method that combines each market’s own momentum with momentum from markets that tend to lead it. It first scales price changes by estimated volatility, then forms moving-average crossover oscillators at…
The article describes implementing k-means clustering in MQL5, using OpenCL to parallelize computations. It motivates a native implementation for cases where Python integration limits access to terminal data, indicators, or event handling, or when clustering…
The article develops a general method for turning a single-timeframe Expert Advisor into a two-timeframe system. A higher timeframe supplies the broad trend direction, while a lower timeframe identifies potential entries. The higher-timeframe trend acts as a…
The article describes a modular MQL5 dashboard for managing positions across several instruments from one chart. Its design separates symbol handling, trade operations, the graphical panel, and the Expert Advisor entry point. A symbol manager parses a…
This article explains how to send selected MetaTrader 5 market information to an Excel workbook for portfolio monitoring and operational risk management. It compares real-time data exchange methods with web-based quote imports, noting that web sources can be…
The article presents MASAAT, a portfolio optimization framework that combines multiple agents, directional price filters, and attention mechanisms. Agents use filters with different thresholds to extract trends at different scales. Cross-sectional attention…
This article extends a trading-platform library by creating concrete indicator objects from an abstract base class and collecting them in a searchable, sortable list. Each object stores properties such as indicator type, timeframe, handle, group, symbol, and…
This installment improves an automated workflow for turning strategy optimizations into a multi-currency expert advisor. The pipeline first optimizes one strategy across symbols and timeframes, selects promising individual instances, then searches for groups…