Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
3,012 dokumenttia
The article presents an architecture for sending live MetaTrader 5 feature vectors to a Python model service. Since MQL5 does not natively support gRPC’s HTTP/2 transport, the design uses a hand-written Protocol Buffers encoder and length-prefixed TCP…
In this 2011 interview, Sergey Nikitin describes the Expert Advisor that was leading the Automated Trading Championship during its second week. It traded EURUSD and EURJPY, used daily charts to determine trend, and relied on trend-watching indicators.…
This article builds an MQL5 library for the Matrix Profile, a time-series method that measures each fixed-length window against its nearest non-overlapping neighbor. Low distances identify recurring shapes called motifs; high distances identify unusual…
This article describes a MetaTrader 5 cross-order system for analyzing continuous historical futures data while placing orders in the currently valid contract. It focuses on Brazilian mini-dollar and mini-index futures, explaining their symbol prefixes,…
This article develops an MQL5 library for describing candle types and patterns, configuring their recognition parameters, and returning statistics from historical analysis. Its class structure stores candle features, trend state, pattern counts, occurrence…
This article shows how to replace hand-written candlestick rules with TA-Lib pattern functions in a Python service connected to a MetaTrader 5 Expert Advisor. The EA sends recent OHLC data to a Flask endpoint; Python builds a time-indexed DataFrame,…
This article explains Segment, Shuffle, Stitch (S3), a learnable module for changing how time-series history is organized before a neural model processes it. S3 divides a sequence into non-overlapping segments, learns priorities that determine their new…
This article explains why maximum drawdown alone gives an incomplete picture of strategy risk: two equity curves with the same peak-to-trough loss can differ greatly in how often they decline, how long they remain underwater, and how quickly they recover. It…
This article presents a channel-breakout entry method intended to capture a change in trend. Channels can slope upward, slope downward, or move sideways, and may be drawn using several channel techniques. The proposed signal occurs when a candle closes…
This article describes a MetaTrader 5 expert advisor that can trade multiple forex and metal pairs from one chart, with an option to run on a single pair. Its signal design combines ZigZag swing structure with the Awesome Oscillator (AO), allowing several…
The article applies supervised learning to three Parabolic SAR and Relative Vigor Index signal patterns that previously failed forward-walk tests. It describes implementing the indicators in Python, connecting to MetaTrader price data, and training a neural…
This technical article explains how ZIP archives store files and describes MQL5 classes for creating, loading, downloading, and extracting archives. It outlines the local file header, file data, central directory, and end record, and explains how filenames…
The article introduces linear and Matérn covariance kernels for Gaussian Process Regression (GPR) and discusses their potential use with financial time series. A linear kernel represents simple linear relationships and is computationally light, making it a…
The article explains Beetle Swarm Optimization (BSO), a population-based optimizer that combines Particle Swarm Optimization (PSO) with Beetle Antennae Search (BAS). Each beetle probes objective values on either side of its position, then combines that local…
The article introduces Markov chains as probabilistic models for transitions among defined states. It explains the transition matrix and the memoryless assumption: the next state depends on the current state and elapsed time, rather than the full path taken…
This installment explains logging handlers as components that receive records from a logger and route them to destinations such as a console, file, or database. It outlines a handler base class with a name, a severity threshold, and common operations for…
This article describes how to extend an MQL5 economic calendar dashboard with controls for currency, event importance, and time range. Users can toggle the filters from the chart panel, select currencies, and use a cancel control to clear filters and remove…
The document explains how to use BotBrains, a block-based editor for creating MetaTrader trading robots without writing code. It surveys the editor’s logic, interface, and code modes, and describes blocks for indicators, orders, chart and market-depth data,…
The document proposes a framework for selecting indicator pairs for trading the Vanguard Information Technology ETF (VGT). It argues that correlated indicators can create redundant confirmation, particularly in a concentrated technology ETF with frequent…
The article explores ways to combine the Fractal Adaptive Moving Average (FrAMA) with the Force Index in an MQL5 trading system. FrAMA is used to describe trend direction or slope, while the Force Index contributes volume-weighted momentum information. The…
The document explains how to use MQL5’s Graphics library to create charts within MetaTrader, including curves from arrays, coordinate pairs, point objects, or functions. It walks through creating a graph, adding and plotting curves, updating the display, and…
The document describes an MQL5 framework for managing related open positions as a single basket. Positions are grouped by an identifier in their comments, then scanned to calculate leg count, long and short volume, aggregate floating profit and loss, and…
This article explains a workflow for deploying a trained Torch time-series forecasting model in a MetaTrader 5 Expert Advisor using ONNX. It covers switching the model into inference mode, collecting and naming its inputs and outputs, exporting it, then…
The article builds a simple automated crossover system and uses it as a baseline for testing simple, adaptive, double exponential, triple exponential, and fractal adaptive moving averages. The signal rule buys when a completed closing price crosses above its…