สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
This article explains a small MetaTrader 5 service used to clarify how a replay system's service, control indicator, and mouse indicator interact. The service creates a custom symbol, supplies it with a sample bar, opens a chart, attaches the indicators, and…
The article distinguishes the gambling use of martingale, which increases stakes after losses, from the mathematical martingale process, whose next value has a conditional expectation equal to its current value. It explains why doubling down can appear…
This article outlines a Python and MetaTrader 5 architecture in which agents analyze different instruments and share signals through a coordination layer. It describes role-based agents, shared portfolio context, and a service that sends structured signals…
This article examines why explainability methods can give conflicting accounts of the same machine learning model. It distinguishes global explanations, which describe overall feature importance or behavior, from local explanations focused on an individual…
This article presents PairPlot, a graphical tool for examining relationships among multiple trading time series. It arranges a histogram for each series and scatter plots for each pair in a cross-table layout, with trend lines as visual aids. The design uses…
This article describes an event-driven bridge that detects closed trades in MetaTrader 5, collects their details, formats them as JSON, and sends them to an external API over HTTP. Its Expert Advisor uses the trade-transaction event handler and filters for…
This article extends an MQL5 history-management library with helper functions for checking how many records are available and retrieving trade history across progressively wider time ranges. It describes checking the previous day first, then expanding the…
The document describes a trend constraint that filters lower-timeframe moving average crossover signals according to the direction of a higher-timeframe candle. Its example uses a faster and slower exponential moving average to generate entries, then…
This installment explains how to simulate changing portfolio weights for a cointegrated stock basket in MetaTrader 5 backtests. Since the live Expert Advisor reads strategy parameters from a database but the Tester cannot access that database directly, the…
This introductory guide presents MQL5 as a trading-focused programming language and explains basic programming ideas for readers without prior coding experience. It introduces high-level and domain-specific languages, identifiers, syntax, comments, data…
The document explains Hierarchical Risk Parity (HRP), a portfolio allocation method that uses asset similarity and risk rather than directly optimizing expected returns. It outlines the process: estimate returns, covariance and correlation; cluster assets by…
This article presents two lightweight diagnostics for MQL5 projects: a profiler that records timing for named code sections and a small assertion-based test harness for pure trading calculations. The profiler aggregates call counts and elapsed time,…
This article extends an MQL5 Kagi chart engine into an Expert Advisor that trades changes in Kagi direction. A Yin-to-Yang transition generates a potential long signal, while Yang-to-Yin generates a potential short signal. Users can enable or disable…
This article develops a reporting toolkit for a continuously shifted walk-forward optimization process. It proposes exporting custom optimization results to XML so that reports can be read by both programs and people. The format separates shared tester…
This article describes an MQL5 Expert Advisor that turns Fibonacci retracement drawing into an interactive chart tool. Users enter swing low and high values in an on-chart panel; the EA calculates retracement and extension levels, labels them with ratios and…
This article adapts angle-based analysis to trading indicators and trend estimation. For comparing two currency instruments, it scales prices into comparable point units and interprets their relative values as an angle, with the indicator intended to show…
The article proposes a market prediction pipeline combining quantum circuit measurements, CatBoost, and a language model. It motivates the design with shortcomings of conventional indicators and reports that an LLM’s analysis changed when prompts or…
This article outlines a forex pair-trading system that compares two instruments through their price ratio. It calculates a Z-score to measure how far the ratio has moved from its historical mean, then uses the sign of the score to choose which instrument to…
This article describes the Bird Swarm Algorithm, a population-based optimization method inspired by flocking and feeding behavior. It represents candidate solutions as birds that can search as producers, follow producers as beggars, feed by combining…
This article proposes a time-of-day trading setup based on overlapping European and US market activity. It argues that volatility rises during a period around the US session open, followed by a quieter move that may continue in the direction of the…
This article explores how to inspect a CatBoost gradient-boosted tree model trained to forecast a future price from market data and technical indicators. It motivates feature interpretation as a way to debug a model, evaluate engineered inputs, guide future…
This tutorial introduces a single artificial neuron using a small set of input-output examples whose relationship is multiplication by two. It presents neural networks as mathematical models that estimate patterns from data, and compares training,…
This article develops a predictive modeling workflow in MQL5 using market price data and matrix operations. It normalizes rows of open, high, low, and close observations, separates training and test samples, and estimates linear-model coefficients with a…
This article describes an MQL5 indicator that uses SQLite to present account trading history and statistics in an interactive dashboard. The interface separates symbol and magic-number lists from detail tables, sorts trade history by time and summary…