สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
The article extends risk analysis for single-asset trading systems, focusing on fixed stop-loss and take-profit exits and fixed trailing stops. It discusses when deal outcomes can be treated as independent and identically distributed, and proposes…
The article compares adaptive learning rate methods for multilayer perceptrons with a one-cycle schedule. It describes adaptive gradient, RMS, mean exponential, and delta approaches, which derive parameter-specific updates from training gradients while…
This article describes a chart-panel indicator that summarizes market conditions across a higher timeframe and two lower timeframes. It uses an exponential moving average to estimate higher-timeframe bias, swing highs and lows to classify lower-timeframe…
The article uses a Darvas box breakout as a case study for supervised machine learning in algorithmic trading. It distinguishes generating trade signals with a model from using a model merely to filter trades produced by an existing strategy. The workflow…
This programming tutorial shows how to extend a minimal MetaTrader 5 indicator that copies input prices into a plot buffer so it calculates an exponential moving average (EMA). It presents the recursive update: combine the current price with the previous…
The article explains how to combine several strategies and symbols in one MetaTrader 5 Expert Advisor (EA) to assess their performance together. It organizes each strategy’s symbol-specific settings and indicator handles in arrays, then processes them in…
The article describes an MQL5 money management class that combines a one-level Haar wavelet filter with an LSTM network to scale position size in volatile, trend-oriented markets. The wavelet step transforms recent log returns into approximation and detail…
This programming guide explains how to inspect four MQL5 structures that carry time and market data: MqlDateTime, MqlTick, MqlRates, and MqlBookInfo. It covers ways to populate these structures from terminal functions and retrieve information such as…
The article introduces parameter search for trading strategies and demonstrates it with a simple moving average crossover. It compares brute-force, grid, and random search in Python, using historical EURUSD daily data over the stated test period, and…
The article explains how to reuse selected MQL5 Standard Library components in expert advisors that must compile under both MQL4 and MQL5. Its approach is to copy the relevant MQL5 headers, place them in an organized MQL4 library folder, and add shared…
This MQL5 tutorial builds on a position-properties Expert Advisor to demonstrate basic Strategy Tester mechanics. It shows how to detect a new bar by comparing its opening time with a stored timestamp, retrieve open and close prices into series-indexed…
This tutorial introduces gradient descent as an iterative way to reduce a model’s cost function. It explains differentiating a function to obtain its gradient, then updating a parameter in the direction opposite that gradient. The learning rate sets the step…
This installment describes updates to a MetaTrader 5 signal monitor, including support for custom indicators and usability improvements. It adds fields for an indicator’s compiled-file path and comma-separated inputs, and enables those fields only when the…
This article presents practical components of an Elite Crystal Evolution Algorithm, a population based optimizer inspired by crystal formation. The population is divided into elite and regular agents. Elite agents conduct local search, while regular agents…
This article introduces database use in MQL5 for a market replication and simulation system, focusing on SQLite because it is integrated with MetaTrader 5. It shows the basic workflow of creating or opening a database file through an MQL5 script, closing its…
This article explains how an automated Expert Advisor can respond to trade server changes through MQL5 events. It emphasizes event driven design: rather than repeatedly polling orders and positions with ticks or a timer, the EA should handle relevant…
The article presents the first part of an MQL5 Expert Advisor designed to support manual trading across multiple symbols. Using the EasyAndFast GUI library, it lays out a panel with tabs, symbol and position tables, chart display, signal-level and…
This article describes an MQL5 framework that monitors manually drawn chart objects and turns price interactions into alerts or trading actions. Building on earlier object detection and coordinate normalization modules, it adds an interaction detector for…
The article proposes combining balance-sheet data from the Federal Reserve, European Central Bank, Bank of Japan, and People’s Bank of China into a global liquidity measure for forecasting currency movements. It explains the intuition that balance-sheet…
The document explains the Black Hole Algorithm (BHA), a population-based method for optimizing continuous or discrete search problems. It initializes candidate solutions as randomly placed stars, selects the current best candidate as the black hole, and…
This tutorial shows how to add visual or audio alerts to MetaTrader indicators. It illustrates alert conditions for crossings between indicator lines, crossings of fixed levels, reversals in indicator movement, changes in an indicator’s position relative to…
The article outlines a workflow for retrieving International Monetary Fund data through its SDMX-JSON interface, parsing the nested responses, handling indicators with different reporting intervals, and caching results. It proposes combining measures such as…
This article explains how MQL5 programs can integrate with the HedgeTerminal API to select, inspect, modify, and close bidirectional positions. It describes installing the library, using its transaction and property functions, submitting trade requests,…
This article presents a prototype spectrum analyzer indicator as an example of building a graphical interface with MQL5 chart objects. It explains two coordinate systems: pixel offsets anchored to a chart window for controls such as labels and buttons, and…