สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
The article describes an MQL5 heatmap that estimates potential liquidation zones from OHLC and volume data. It marks candles whose volume exceeds a moving average, uses candle direction to choose a level below or above the candle, and applies a user-defined…
This installment of a market replay and simulator series turns a Chart Trade interface into a functional indicator that can communicate with an Expert Advisor. The indicator declares a data buffer, initializes it, and updates it during calculations and chart…
The article shows how to build an Expert Advisor around a trend filter and channel-boundary entries. It uses daily MACD movement over consecutive bars to determine direction, then looks for hourly price rebounds from Envelopes. Stop loss, take profit,…
This article explains how regression metrics assess model predictions and how they differ from loss functions used during training. It reviews MAE, MSE, RMSE, R-squared, MAPE, MSPE, and RMSLE, describing their units, sensitivity to large errors,…
The article develops a modular approach to ZigZag indicators in MetaTrader 5. It frames the indicator as a line connecting local highs and lows, then separates its implementation into source-data selection, direction-change rules, and plotting. Possible…
The article explains SparseTSF, a compact approach to long-horizon time-series forecasting that assumes a known period in the input data. It splits a sequence into period-aligned subsequences, forecasts those subsequences with shared linear parameters, and…
This introductory programming article explains three MQL5 concepts used to organize trading software: structures, classes, and time functions. Structures group related fields, which the examples illustrate with records containing several attributes. The…
The article describes designing an interactive MetaTrader 5 panel to speed up common trading operations. Its proposed controls cover opening market positions, placing pending orders, modifying or closing positions, editing or deleting pending orders, and…
This article presents a prototype pipeline for translating symbolic brain-computer interface commands into MetaTrader 5 trade actions. A Python Flask server simulates commands such as buying, selling, closing positions, or holding; an MQL5 Expert Advisor…
This article combines general capital-management advice, an explanation of MetaTrader 5 report metrics, and a description of a Python home-accounting application for traders. It recommends separating trading funds from personal money, maintaining an…
The article explains Pretrained Decision Transformer (PDT), a reinforcement learning approach that first trains on offline trajectories without reward labels and later adapts to a reward-defined task. During pretraining, an actor predicts actions from past…
This article describes a reusable MQL5 library for measuring portfolio-wide exposure and checking it before an EA opens a trade. It distinguishes account-wide monitoring from a magic-number filter, then outlines a snapshot of positions, pending orders,…
The article explains InjectTST, a Transformer method for forecasting multivariate time series that combines independent channel processing with selectively shared global context. Separate channel pathways use a shared encoder, positional information, and…
The article proposes encoding EURUSD market features through an eight-qubit simulated quantum circuit, then using statistics from its measured state distribution as inputs to a CatBoost forecasting workflow. Returns, volatility, and RSI are normalized into…
This installment develops basic controls for a MetaTrader 5 market replay system. The preceding system could generate one-minute bars, but users had little control over playback and could not conveniently pause or choose a starting time. The article sets out…
The document explains Mind Evolutionary Computation (MEC), a population optimizer modeled on competition and information exchange among groups. In the basic method, agents form groups, search around each group’s best candidate, and use group comparisons to…
This article presents an MQL5 routine that takes recent closing prices, ordered with the newest first, and returns a one-step-ahead close forecast. It estimates differencing order with a variance-based heuristic, differences the series, fits ARMA candidates…
This MQL5 cookbook describes how to extend a multi-currency Expert Advisor so that, after a test, it writes deal history and balance series for each symbol to a CSV report. The report includes deal attributes such as symbol, type, direction, price, profit,…
This article investigates a reported Linux problem in MetaTrader 5’s built-in OpenCL support: GPU devices appear in the platform’s device list, but attempts to select them with GPU-specific context flags fail. The author proposes that the failure lies in…
This installment of a market simulation series explains how to turn MetaTrader 5 tick data exported as a tab-delimited CSV into a table in a MetaEditor database. It walks through creating a clean database, choosing the import option, selecting the file,…
The article presents a way to preserve changes to an Expert Advisor’s settings in a single append-only binary file. Each fixed-size record groups version metadata, adjustable trading parameters, optional performance metrics, and an integrity checksum. The EA…
The article turns the three-candle Fair Value Gap concept into a reusable detection framework. It defines bullish gaps where the later bar’s low exceeds the earlier bar’s high, and bearish gaps where the later bar’s high falls below the earlier bar’s low. It…
The article describes a two-stage forecasting system for financial time series. A linear autoregressive model uses a 25-feature input set, including price lags, transformed values, indicators, and cyclical time features. A U-Transformer then models the…
This article presents techniques for making technical indicators easier to read in MetaTrader 4. Using RSI and a smoothed RSI as examples, it shows how to mark line crossings in a separate buffer, highlight values relative to levels, identify local tops and…