สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
This article explains how to make a MetaTrader 5 trading panel respond to user actions. It uses OnTick to refresh account equity, balance, and server time while the information view is active, and OnChartEvent to detect clicks on chart objects. The panel…
The article introduces PatchTST, a Transformer approach that groups consecutive time steps into patches before modeling a multivariate time series. It treats each variable as a separate univariate channel, shares model parameters across channels, and uses…
The article explains how MQL5, C#, and C++ applications can encrypt and decrypt a shared license object. It uses a hypothetical licensing workflow in which a record holds user details, permitted trading accounts, product names, and expiration information.…
The article shows how an MQL5 custom moving average indicator can respond to keyboard events so a trader can change its method, period, and chart shift while it is running. Because indicator input parameters cannot be modified directly in code, the…
The article describes a bridge application that lets MetaTrader terminals exchange files through Google Drive. A separate C# program handles authorization and cloud operations, while terminal applications send it requests. This keeps the provider’s computer…
The article adapts a conditional generative adversarial network to forecast financial time series within an MQL5 expert advisor. It describes a generator and discriminator, both based on a multilayer perceptron: the generator uses prior close-price changes…
The article compares MetaTrader 5 and QUIK using three measures: elapsed time for sequential confirmed market orders, time to send a sequence of unconfirmed orders, and the frequency of market-depth updates. The tests were run on the same hosted computer,…
This article explains the event model and core classes of a reusable MetaTrader 5 trading engine. It proposes routing market and timer events through a centralized handler, so strategy logic can respond consistently to ticks, new bars, timers, and order-book…
The article describes a MetaTrader 5 workflow for combining many optimized strategy parameter sets in one expert advisor. It focuses on EURUSD hourly trading and uses perceptrons built from TEMA slope inputs, with optimized weights and a threshold parameter…
The document proposes using the coefficient of determination to assess how closely a strategy’s balance or equity curve follows a linear trend. It contrasts this measure with common tester statistics such as net profit, profit factor, expected payoff, and…
The document presents the second-level path signature, especially its antisymmetric component called Levy area, as a rolling measure of ordering between two time series. Rather than scanning candidate lags as cross-correlation does, it treats paired…
This document describes a setup for optimizing selected Expert Advisor parameters on a recurring schedule. One MetaTrader 5 instance runs the live EA and an optimizer EA; a second instance runs the Strategy Tester. The optimizer prepares configuration and…
The document explains how to create MetaTrader 5 custom symbols, configure their contract properties, and populate them with bar or tick history. Imported data can come from an existing symbol or a third party, provided it follows the platform’s required…
The article develops the first two stages of the Mapper topological data analysis pipeline for price point clouds: assign each point a scalar lens value, then divide the lens range into overlapping intervals called a cover. It describes three lenses:…
The article presents an alternative way for a MetaTrader 5 Expert Advisor and a service to exchange data when terminal global variables are the communication channel. Since those variables hold only double values, the method overlays a double with a byte…
The article explains standard deviation as a measure of how dispersed prices are around their average, then outlines a manual calculation and the corresponding MetaTrader indicator settings. It presents three rules: compare the current standard deviation…
The article explains symbolic regression as a way to model relationships between input data and a target without choosing a fixed equation form in advance. It represents candidate models as expression trees built from randomly selected coefficients,…
The article describes a market-neutral forex pair-trading approach that buys one instrument and sells another when their spread moves unusually far from its typical level, then exits as the spread contracts. It discusses using correlation to select related…
The article explains how the MetaTrader 4 strategy tester reconstructs price movement and why tick-based simulation matters. It contrasts testing from completed bars, where future information may leak into calculations, with feeding modeled price changes…
This tutorial uses a single sigmoid neuron trained on a small AND-gate dataset to explain the cost of numerical gradient estimation. In the initial version, the code estimates changes in the loss by repeatedly evaluating the cost function after perturbing…
This article develops basic support in the DoEasy library for creating standard chart objects from programs and tracking changes to their properties. It adjusts which properties different object classes report as supported, distinguishing objects constructed…
This programming tutorial shows how MQL5 templates can replace overloaded functions when the same operation is applied to arrays of different types. Its starting example computes means from arrays of floating-point and integer values. The author compares…
This article examines why a chart mouse indicator that estimates time remaining in a bar can become stale when few quotes arrive. Because MetaTrader 5 calls the indicator’s calculation handler when it receives quote updates, a spread-based timer may stop…
This document introduces the CFTC’s Commitments of Traders and Traders in Financial Futures reports as sources of aggregated futures positioning. It describes commercial hedgers, non-commercial speculators, and smaller traders, and explains how TFF breaks…