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
The article outlines a workflow for adding a Hidden Markov Model (HMM) volatility filter to a moving-average trend-following strategy. It defines volatility as the standard deviation of returns over a rolling window, classifies observations into high and low…
This article develops an MQL5 library collection for working with signals available through the MQL5.com Signals service. The collection is intended to hold signal objects so users can search and sort them by attributes, filter free and paid offerings, and…
The article explains how to build a local Model Context Protocol server that lets compatible AI clients request data from, and send trading operations to, a MetaTrader 5 terminal. It describes a four-part structure: mappings between readable labels and…
The article describes a software design for building population-based optimization algorithms around a shared base class. It proposes common representations for algorithm parameters and search agents, along with reusable utilities for scaling, random-number…
The author argues that complex processes may contain detectable structure and recounts an earlier attempt to forecast lottery outcomes as motivation for searching for patterns in markets. For Forex, the article recommends observing several short-term charts…
The article describes ways to label historical data for machine-learning trend strategies. Its basic method smooths closing prices with a Savitzky–Golay filter, estimates trend direction from the smoothed series, and normalizes the gradient by rolling price…
The article proposes a quick visual workflow for evaluating trading ideas. A trader adds buy and sell signals to an indicator, then uses a balance indicator to display simulated entries, exits, balance, and equity on the same chart. The author illustrates…
The article explains how Fibonacci retracements measure how much of a prior price swing has been recovered, while extensions project levels beyond that swing. It describes calculating these levels from swing points and shows how the resulting ratios help…
The article explains double top and bottom patterns as repeated tests of a resistance or support area that fail to break through, potentially helping a reversal develop. It compares three entry approaches: trading a neckline break, entering after a return to…
The article explains how OpenCL enables parallel calculations on compatible CPUs and GPUs and how this capability can be used by MQL5 programs. It outlines hardware and software prerequisites, distinguishes GPU driver installation from CPU SDK setup, and…
The article outlines an MQL5 Expert Advisor for the Profitunity approach, combining Bill Williams’ Fractals, Alligator, Awesome Oscillator, and Accelerator Oscillator. It describes the indicators’ roles: fractals mark local extremes, the Alligator’s moving…
The article addresses the challenge of choosing a technical indicator’s lookback period: short periods can react to noise, while long periods may lag. It proposes feeding readings from many periods into a dimension reduction method, focusing on UMAP to…
This article examines the core class behind an interactive Chart Trade panel for MetaTrader 5. The panel is built as a floating chart embedded in an indicator, with editable regions, mouse-position checks, and a template that stores layout and display…
This educational article introduces the Moore–Penrose pseudoinverse and begins a from-scratch MQL5 implementation using arrays rather than the language’s built-in matrix tools. It first demonstrates the library pseudoinverse result for a small matrix, then…
The article presents an MQL5 service that periodically reads the properties of trading signals available in the terminal, compares each snapshot with previously stored values, and writes updated records to MySQL when it detects changes. It organizes…
The article describes an object-oriented MQL5 wrapper for running a model exported in ONNX format inside MetaTrader 5. It outlines the inference lifecycle: load the model, define input and output tensor shapes, pass a fixed-size feature vector to the…
This article adapts a single-layer convolutional neural network (CNN) for a trading signal in MQL5. It explains padding input matrices, convolving kernels across data, applying activation, and pooling feature maps; it also discusses backpropagation for…
The article presents the Artificial Electric Field Algorithm (AEFA), a population-based optimization method inspired by electrostatic attraction. Candidate solutions are particles in a search space; their fitness determines normalized charges, and forces…
This article explains how MQL5 represents colored indicator plots when an indicator handles multiple symbols and timeframes. A plotted series may need one or more data arrays, depending on its drawing style, plus a separate color-index array for colored…
This article describes the logic layer of a C# graphical add-on for managing optimization runs across multiple MetaTrader terminals. It organizes the application into classes for terminal configuration, directory structure, optimization reports,…
This article describes a spectrum-fitting stage in a multifractal modeling pipeline. Starting from a scaling function τ(q), it uses a Legendre transform to estimate the singularity spectrum f(α), with a central finite-difference approximation for the…
This article outlines statistical tools for evaluating a sequence of trade results. It uses the central limit theorem to explain why averages of samples can approach a normal distribution, while cautioning that financial returns and their derivatives can…
The article reviews ways to detect when a new chart bar appears and develops a more reusable event-handling approach for MQL5. It identifies problems with a simple function that stores the last bar time in a static variable: repeated calls can interfere with…
The article explains the Opening Range Breakout approach and demonstrates how to automate it with an MQL5 expert advisor. The EA records the high and low of an initial session candle, then looks for a bullish candle close above the high or a bearish close…