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 installment of an MQL5 tutorial extends a ChatGPT-connected trading assistant with longer multiline prompts, a sidebar for saved conversations, and initial signals informed by chart data. It describes modularizing the program, refining text display and…
This interview profiles a novice Automated Trading Championship participant and summarizes his GBPUSD Expert Advisor. The robot uses MACD to generate buy or sell signals, then applies manually estimated probabilities of subsequent price movement to decide…
This article introduces simple recurrent neural networks (RNNs) for forex time-series forecasting and explains how their hidden state carries information across sequential inputs. It outlines the recurrent computation and backpropagation through time,…
In this interview, Automated Trading Championship participant Evgeny Gnidko describes an Expert Advisor that trades EURUSD using pending orders at levels calculated with the standard MetaTrader ZigZag indicator. The robot also applies signal filtering and a…
This article describes an Expert Advisor that turns selected MetaTrader chart objects into trade instructions. Traders configure trend lines, horizontal and vertical lines, channels, and Fibonacci retracements through standard object properties. Prefixes…
This tutorial describes a single-position MQL4 Expert Advisor built around MACD crossovers, with an exponential moving average used as a directional filter. Long entries require MACD to be below zero and turning upward across its signal line; short entries…
The article presents a signal framework for Expert Advisors intended to work in both MQL4 and MQL5. A signal class evaluates a market condition, while a container combines multiple signals. For entries, non-neutral signals must agree on direction; a void…
This article outlines a workflow for running a local language model with Ollama and adapting it to produce structured trading signals. It describes downloading a small base model, defining trading rules and output fields in a model configuration, and testing…
The article explains a reinforcement learning approach that trains a neural network to choose trading actions directly. Unlike Deep Q-Learning, which estimates expected rewards for actions, the policy model outputs a probability distribution over actions.…
The article walks through retrieving historical XAU/USD data from MetaTrader 5, preparing it in pandas, and visualizing price, tick volume, and moving averages in Jupyter. It also describes further analysis and a broader workflow for combining Python data…
The article explains how a fixed-capacity circular buffer can replace repeated array shifting when maintaining rolling market data in MQL5. Rather than moving every stored value on each update, the buffer advances a head index and overwrites the oldest slot,…
The article derives the Flower Volatility Index (FVI) from the Cartesian components of a Rose Curve and presents it as a bounded oscillator for trend analysis. It explains how the curve’s parameter ratio affects its petal geometry and oscillation period,…
The article proposes pairing a base time-series classifier with a metamodel that filters difficult or unfavorable trading examples. The metamodel uses a longer history window, labels candidate situations as useful or unsuitable, and guides relabeling and…
The article describes a MetaTrader analysis tool that combines price action with Bollinger Bands, the Relative Strength Index, and Average True Range. Its example signal logic considers a sell when RSI is above the stated overbought threshold and price is…
This installment describes a software design for representing indicators as objects in the DoEasy MQL5 library. It introduces an abstract base indicator class, intended to be extended by standard and custom indicator classes. Each object records properties…
The article presents a manual-trading risk manager for MetaTrader that monitors daily, weekly, and monthly loss limits, with an optional daily profit target. When a limit is reached, the tool closes open positions and displays a warning; because it is…
This article explains how to extend an ONNX model parser and display the network as an interactive graph in an MQL5 chart panel. It derives connections by matching node output names to input names, then assigns nodes to depth-based ranks so branches appear…
This article presents the Candle Pressure Index (CPI), a price-action indicator that estimates buying or selling pressure from a candle’s closing location within its high-low range. The normalized value runs from bearish pressure near the low, through…
This article tests whether supervised neural-network filters can improve selected signal patterns formed by the Awesome Oscillator and Envelope Channels. It introduces dot-product cross-time attention, which scores relationships between sequence elements and…
This article explains a U-shaped Transformer approach for time-series modeling and its implementation for trading research. The architecture groups Transformer layers and uses patch merging and splitting to represent the series at different scales. Skip…
This article describes automating the second stage of a multi-currency Expert Advisor optimization workflow: selecting groups of individually optimized strategy instances whose combined behavior may improve drawdown or balance-curve smoothness. Instead of…
The article introduces options and their terms, exercise and settlement styles, the Black–Scholes model, and the principal Greeks. It emphasizes delta as the sensitivity used to approximate option exposure with positions in an underlying asset. It also…
This article demonstrates the decorator pattern for adding logging, execution timing, and threshold filtering around MQL5 indicators without changing their calculation classes. A shared interface gives raw indicators and wrappers the same GetValue and…
The article outlines a staged method for adapting simple MQL4 price indicators, using MACD as its example. It first changes the legacy calculation routine to accept bar counts, prior-calculation state, output buffers, and inputs as arguments. The code is…