สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
This article presents an updated version of a MetaTrader application for testing candlestick patterns. Changes include a reorganized interface, individually selectable patterns and timeframes, date-range controls, and separate trend-threshold settings for…
This article develops a simple trading dashboard for a MetaTrader chart and explains how to make the interface movable. The example dashboard includes a title bar and body, labels, a lot-size field, and Buy and Sell buttons. The implementation divides chart…
This article describes the first stage of adapting a MetaTrader trading library written for MQL5 so it can compile and operate in MQL4. The starting point is to compile the library under MQL4 and work through the errors, many of which arise because MQL4…
This article explains how a MetaTrader replay service can use a control indicator’s buffer to communicate current chart information. The indicator refreshes that buffer both when chart events occur and when new quotes trigger calculation, helping keep its…
The article describes Saplings Sowing and Growing (SSG), a nature-inspired population optimization method in which candidate solutions are treated as trees and parameters as branches. It presents an implementation that starts with randomly distributed…
The article develops a MetaTrader Expert Advisor that combines Heikin Ashi candles with fractal swing points to identify breakouts. A bullish candle with no lower wick closing above a recent swing high triggers a long setup; a bearish candle with no upper…
This article ports a set of bar-level market microstructure estimators to MQL5 and describes a class and chart indicator for calculating and displaying them. The measures include Roll spread and impact, Corwin-Schultz spread and intraday volatility, and…
The article explains Time-MoE, a decoder-only Transformer foundation model for time-series forecasting, and sketches how its components could be implemented in MQL5. It describes converting each time step into a token, embedding features with SwiGLU, and…
The article proposes maintaining a parallel history of virtual positions generated by a trading system. The virtual trades follow the same entry signals and track stop-loss, take-profit, trailing-stop, and signal-based exits, while a separate filter decides…
This article continues a description of a chaotic optimization algorithm for searching solution spaces. It combines logistic, sinusoidal, and tent maps with an initial broad search, weighted-gradient refinement, and a final local search whose scope narrows…
The document introduces Bill Williams’ Market Facilitation Index (BW MFI), calculated as the high-low range divided by volume, and interprets its movement alongside changes in volume. Rising or falling values for both are treated as distinct market states,…
This installment analyzes a simple grid strategy that adds positions at fixed price intervals, increasing each new order’s size by a multiplier. It explains how weighted average entry price determines breakeven and how the chosen direction, initial lot size,…
The article describes a cross-platform Expert Advisor for MetaTrader 4 and 5 that uses a trader-defined entry and stop-loss level to calculate position size from a fixed dollar or percentage risk budget. It also sets a take-profit level from a configurable…
This interview recounts one participant's approach to automated trading and his robot in the 2012 Automated Trading Championship. The featured system was a simple moving-average strategy, generated with the MQL5 Wizard and adjusted for competition rules. Its…
The article proposes organizing economic calendar observations with database tables and category-theory mappings. Its motivation is that calendar events differ in units, formats, geography, and meaning: some publish numeric indicators, while others are…
The article describes a two-stage workflow for measuring costs and using them to set more realistic triple-barrier labeling thresholds. An MQL5 script gathers broker-specific spread history, hourly spread averages, swap settings, and symbol details into a…
This guide combines DeMark Sequential with Murray-Gann price levels to interpret trend development and possible reversals. Sequential begins with a directional setup based on closes relative to earlier bars, confirms a run of qualifying bars, waits for an…
This article explains an attempt to adapt N-BEATS, a residual time-series forecasting architecture, for a forex Expert Advisor in MetaTrader 5. The model decomposes a series through stacked blocks that successively explain historical input and contribute…
This article describes a practical MQL5 adaptation of Multitask-Stockformer, a neural architecture for financial time series. It first outlines the framework’s use of discrete wavelets to split signals into low-frequency trends and high-frequency…
The article presents a reusable MQL5 journal that records a position’s path while it is open, rather than relying only on the final deal history. Called on every tick, it tracks maximum adverse excursion and maximum favorable excursion in account currency,…
The article proposes using cross-validation predictions to identify training examples that a classifier repeatedly mislabels. A primary CatBoost model is trained on examples judged more predictable, while a second classifier learns across the wider dataset…
The article describes an implementation component for a segmental structured convolutional neural network intended to process noisy, nonstationary financial time series. Its design first decomposes a series into trend, seasonal, short-term, and residual…
The article introduces chaos theory concepts such as nonlinear dynamics, sensitivity to initial conditions, and limited predictability, while distinguishing mathematical chaos theory from Bill Williams’ looser use of the term. It then presents an indicator…
This article describes a MetaTrader workflow for examining completed account trades and testing hypothetical exit rules. An expert advisor first exports deal history, with optional filtering by symbol or magic number, to a file. A second run in the strategy…