สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
This tutorial explains how to implement the True Strength Index (TSI) as a custom MQL5 indicator. TSI normalizes a double-smoothed close-to-close momentum series by a double-smoothed series of absolute momentum, using two exponential smoothing periods. The…
The article presents a modular design for an Expert Advisor that combines custom and built-in trading signals through the MQL5 Standard Library and Wizard. Signal modules can be developed independently, assigned weights, and given different roles: primary…
The document outlines classical CAPM and proposes a forex indicator that replaces market beta with a risk premium scaled by a currency pair’s historical volatility. It annualizes volatility using a square-root-of-252 factor, combines the resulting premium…
This article presents a method for tracking the net position volume attributable to a particular Expert Advisor, symbol, and magic number in MetaTrader 5. It adds buy deal volumes and subtracts sell deal volumes, starting from the most recent point in deal…
This article introduces Market Profile as a price histogram used to interpret auction activity and the balance between supply and demand. It describes balanced sessions as tending toward a bell-shaped distribution, while trending or imbalanced activity can…
This programming tutorial explains how to place data and the operations that use it inside an MQL5 structure to give the code a clearer purpose. Its example stores an array and provides methods to set the values and calculate their average and median. The…
This article proposes a trading system that pairs a discrete Fourier transform (DFT) with a leaky integrate-and-fire spiking neural network. The DFT examines a rolling series of prices or indicators such as MACD and RSI, selects the strongest frequency…
This article presents a constrained, restartable grid Expert Advisor informed by Aldo Taranto’s research on bidirectional grid processes. It contrasts the grid’s accumulating losses across traversed levels with the faster loss growth of martingale doubling,…
This article introduces Prophet’s trend, seasonality, changepoint, and holiday components, then applies the model to hourly EURUSD data from MetaTrader 5. It defines the target as each bar’s high-to-low range, converts timestamps and volatility into the…
This article builds a historical tester for four candlestick patterns: bullish and bearish pin bars and engulfing patterns. It first defines conditions for detecting each pattern on closed bars, then implements an MQL5 Expert Advisor that opens trades in the…
This article improves a MetaTrader 5 Expert Advisor’s chart indicators so traders can identify whether a pending order is for a buy or sell and whether it is intended as a day trade or a longer swing trade. Bitmap icons encode direction and holding period,…
The article studies discrepancies between a quoted EURGBP rate and a synthetic rate derived from EURUSD and GBPUSD, treating deviations as possible trading signals. It reports statistics from two months of five-minute data, including negative skew, heavy…
This article shows how to model withdrawals during MetaTrader 5 strategy testing and explains how they affect account balance, equity, and drawdown reporting. It proposes configurable withdrawal schedules and amounts, with withdrawals calculated either as a…
The article argues that predictive machine-learning models depend on meaningful inputs and labels, and that associations in historical data do not by themselves demonstrate cause and effect. It introduces causal inference concepts alongside the history and…
This article explains how to extend the CStrategy trading engine with custom Expert Advisors and supporting classes. It presents a Singleton logger that stores typed messages with timestamps, source information, and error details, and describes accessing…
The article explains how to construct a Kagi chart in an MQL5 Expert Advisor. Unlike time-based candlesticks, Kagi lines extend with price movement and reverse only after crossing a chosen threshold. The implementation supports either a fixed price-step…
The article introduces genetic algorithms as population-based optimization methods and explains how candidate solutions are represented as chromosomes. It covers binary encoding of integer and floating-point attributes, including Gray coding to make…
This article describes an automated pipeline that combines Smart Money Concepts with a machine-learning filter. A Python process retrieves historical XAUUSD hourly bars, detects Order Block, Fair Value Gap, and Break of Structure events, labels events by…
The article explains partial information decomposition (PID), which separates the information two indicators provide about a target into redundant, unique, and synergistic parts. It describes three alternative redundancy definitions—I_min, I_MMI, and…
The article describes an MQL5 Expert Advisor for trading breakouts from the Asian session range. It records the session high and low over configurable start and end times, then places pending buy-stop or sell-stop orders beyond the range according to a…
The article presents a binary classifier for predicting the direction of the next Renko bar on EURUSD. It converts five-minute price data into Renko bars using an ATR-based block size, then builds features from recent bar directions, directional streaks, and…
The article explains TimeFound, a Transformer-based foundation model designed to forecast time series across domains, including financial data. Its central preprocessing idea is multi-scale patching: segments at several resolutions are projected into a…
The article describes a proposed integration of ST-Expert, a graph-based mixture-of-experts approach, with Extralonger, a modular Transformer framework for time-series forecasting. It frames market data as both sequences and networks: assets or time points…
The article contrasts directional classification with regression for trading forecasts. A classifier predicts direction but not the size of a move, so hit rate alone can conceal the effect of gains and losses. The proposed regression targets measure future…