สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
This article presents a discretionary trade-entry framework that combines subjective support, resistance, and midpoint reference levels with three two-candle patterns. The patterns describe wick rejection, a tweezer-like pair with similar candle bodies, and…
This practical guide uses a rolling z-score indicator to demonstrate how MetaEditor’s sampling profiler can locate expensive code. It explains how to start profiling on live or historical data and how to read Self CPU, which attributes samples to a…
This article describes interface and visualization upgrades for an MQL5 tool that displays a binomial distribution in three dimensions. It adds a segmented curve made from box primitives to show the probability mass function with clearer depth,…
This article explains why classifier probabilities need calibration before they are used for trade sizing. A model can rank opportunities well while overstating their true win rates; that error can flow into probability-based sizing and Kelly-style…
The article introduces gradient boosted decision trees and explains how XGBoost and LightGBM build an ensemble sequentially, fitting trees to reduce the errors of earlier predictions. It covers practical distinctions from methods such as logistic regression,…
This article describes an Expert Advisor that combines an ONNX price classifier with SMA and EMA trend filters. Predicted direction is used to trigger trades only when price also lies on the corresponding side of both moving averages. The system periodically…
The article explains Ebola Optimization Search Algorithm (EOSA), a population-based metaheuristic inspired by disease transmission. It maps close contact to local exploitation around a strong solution and travel to exploration across the search space, while…
The article outlines a trading bot that connects an MT5 Expert Advisor to a Python server over a socket. The EA sends a symbol and Twitter API credentials, requests sentiment data at regular intervals, and receives a sentiment value. The described trading…
In this interview, Automated Trading Championship 2012 participant Sergey Abramov discusses the design and behavior of his trading robot. He says its entry timing was selected by optimizing results from prior periods, with one main entry time during exchange…
The article describes the Blue Monkey algorithm as a population-based method for optimizing discrete trading robot parameters. It divides adult candidates into groups, moves each toward its group’s best candidate, and separately moves a smaller offspring…
The article explains how to draw horizontal bar diagrams on MetaTrader 5 charts for distributions such as tick volume by price or time. It separates the work into preparing data coordinates and managing the graphical objects, which may be horizontal lines or…
The article describes integrating MetaTrader 4 with Microsoft SQL Server through a DLL and database procedures. Its example stores incoming tick time, symbol, bid, and ask values in a SQL table, with the server assigning its own insertion timestamp. Related…
This installment revises an MQL5 market replay service to make one-minute bar construction more consistent and efficient. The earlier approach could take longer than a minute to build bars, particularly during volatile periods, creating a misleading…
This project explains how an MQL5 Expert Advisor can use Binance’s API to retrieve candlestick data for an asset that is not available in the MetaTrader terminal. It parses the returned candle fields, including OHLC prices and opening times, then checks…
The article argues that common regression losses such as RMSE, MSE, and MAE can favor a forecast near the target’s historical mean. In noisy financial data, a model that predicts the average return may score well without learning a signal useful for trading.…
The article presents a workflow for using CatBoost to filter trades from a moving average crossover trend-following strategy. The model is trained to classify trade outcomes as wins or losses, using market features recorded for each trade. The proposed role…
This article explains how to make a chart-based MetaTrader Expert Advisor calculate order sizes and protective levels across instruments with different contract specifications. The author compares Brazilian shares, futures contracts, and forex, highlighting…
This article investigates why an automated optimization pipeline failed to produce a final Expert Advisor database for one project. It traces the project through its stages by inspecting SQLite records for stages, jobs, tasks, and completed passes. Short…
This article continues a machine learning trading project by choosing binary classification and training an XGBoost model on engineered features. It describes separating labels from numeric inputs, fitting the classifier, and evaluating predictions on a…
This article adds Golden Cross and Death Cross logic to a multi-strategy MetaTrader 5 Expert Advisor. The signals are based on a faster moving average crossing above or below a slower one, with the commonly cited long-period pairing used as an example. The…
This installment describes the early implementation of a visual order-management interface for a MetaTrader 5 Expert Advisor. The intended chart display includes controls and markers for order price, stop loss, take profit, and closing actions, with related…
The article presents an MQL5 indicator concept for identifying psychologically salient price levels across instruments with different quote precision. Its method first rounds prices to the tradable tick size, converts the normalized value to a string at the…
This article surveys data preparation for neural network classifiers, focusing on filtering mislabeled training examples and reducing input dimensions. It compares data-level noise filtering with methods that try to make the classifier itself more robust,…
This article presents a defensive MQL5 foundation for intraday market measurements, motivated by irregular observations, fat tails, volatility clustering, and sparse history. It describes guards for division, logarithms, square roots, exponential overflow,…