আমাদের AI এজেন্টরা যে বই, গবেষণাপত্র, নিবন্ধ ও কোড পড়েছে, সেগুলোর সারাংশ ও মূল ধারণা লিখেছে Stratmill-এর গবেষণা এজেন্ট। প্রতিটি পাতায় মূল উৎসের লিংক রয়েছে।
3,012টি নথি
This article explains how to build an MQL5 Expert Advisor to identify and trade the 5-0 harmonic pattern. It describes the six turning points and the bullish and bearish structures, then uses swing highs and lows to assemble candidate legs. Fibonacci…
GoertzelBrain combines Goertzel frequency analysis with an ensemble of online-trained neural networks to turn detected cycle structure into a directional confirmation signal. It extracts cycle period, amplitude, spectral confidence and their changes,…
This article adapts Directional Diffusion Models, originally developed for graph representation learning, to financial market data. Standard diffusion adds isotropic Gaussian noise, which can erase structure quickly in anisotropic data. The proposed method…
The document presents a workflow for labeling financial time-series data by trend. It retrieves bars from a MetaTrader 5 terminal with Python, converts the returned data into a pandas DataFrame, converts timestamps, and selects the close-price series for…
The document formalizes a weekend-gap setup using Friday’s close and Monday’s open as the gap boundaries. For a gap down, it seeks a bullish candle close back above the lower boundary and targets the Friday close; for a gap up, it seeks a bearish close below…
The document describes an MQL5 chart indicator for comparing price movements across the current instrument and five user-selected symbols. It displays raw prices as lines, bars, or candlesticks and lets users choose where the series should be aligned: at a…
The document explains FITS, a compact neural-network approach to time-series forecasting. It transforms an input window with the fast Fourier transform, interpolates its complex frequency representation using a complex linear layer, then applies the inverse…
The article presents Bag-of-SFA-Symbols (BOSS) as a way to classify market regimes by converting price windows into symbolic words. Each window is z-normalized to reduce sensitivity to price level, transformed with a low-pass Fourier representation to retain…
The article explains SSCNN, a neural architecture for multivariate forecasting that decomposes a series into long-term, seasonal, and short-term components plus residual information. A temporal attention normalization layer selects relevant observations for…
The article introduces OpenCL as a way to run computational workloads in parallel from MQL5, using a calculation of pi to illustrate the difference between a single CPU loop and an OpenCL implementation. It outlines the roles of vendor runtimes and SDKs, and…
This article presents a MetaTrader 5 expert advisor that uses fast and slow exponential moving average crossovers to start long or short trades. The example checks for signals on completed bars, opens an initial order with configurable volume and stop…
This introductory article explains how a risk-management class for MetaTrader 5 could track daily, weekly, total, and per-trade losses, as well as profits. It describes setting thresholds, checking account conditions during operation, and stopping or closing…
This installment of a candlestick trend-constraint indicator series discusses ways to identify possible trend changes, including moving averages, candlestick patterns, trendlines, and support and resistance. Its implementation adds a reversal signal based on…
The article describes an include-file risk manager for MetaTrader 5 expert advisors. It outlines conservative, moderate, aggressive, and custom modes, with limits for daily, total, and per-trade risk. It also compares balance-based and equity-based drawdown…
This article describes a workflow for training a Twin Delayed Deep Deterministic Policy Gradient (TD3) agent in Python and deploying its actor network in an MQL5 Expert Advisor through ONNX. It presents the trading task as sequential decision-making:…
This introductory tutorial explains how MQL5 programs can communicate with external servers using HTTP requests. It outlines the two WebRequest function forms and the roles of methods, URLs, headers or cookies, timeouts, byte-array request bodies, response…
This article explains Charged System Search (CSS), a population-based optimization method inspired by electric charges and Newtonian motion. Candidate solutions are modeled as charged spheres. Their fitness determines their charge, while forces between…
In this championship interview, developer Vladimir Tsyrulnik describes an automated USD/JPY approach that interprets market state at selected points in a bar’s lifetime. Its directional forecast is based on an index derived from Bulls/Bears Power, with other…
This article outlines an intraday Expert Advisor built around pullbacks to an exponential moving average. Trend direction is inferred from price relative to the average, while an interaction is identified when a candle crosses the line and closes back on the…
This installment describes adapting a MetaTrader 5 replay and simulation system so its control indicator works as a module. The system moves away from terminal global variables toward custom user events for communication among its service, mouse indicator,…
The article explains Local Feature Selection (LFS), a classification method that chooses a potentially different subset of predictors for each training sample or local region. Instead of ranking features by their overall predictive value, it seeks features…
The article presents a way for MQL4 and MQL5 indicators to read one another’s data buffers without repeatedly calling the standard custom-indicator access functions. Its approach passes a dynamic array’s memory address to a small C++ DLL, then uses that…
The article turns Larry Williams’ smash day reversal idea into objective rules for an Expert Advisor. A bullish setup begins when a bar closes below a configurable number of earlier lows; a bearish setup closes above earlier highs. Outside bars are excluded,…
The article explores whether forecasting changes in RSI can provide a useful proxy for forecasting direction in Deriv’s Boom 1000 synthetic market. Using 100,000 one-minute observations, it compares a direct price-direction target with a target based on…