สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
This article describes modular programming for trading robots: divide an expert advisor into independent components with clear inputs and outputs so one component can be replaced without rewriting the rest. It recommends keeping core trading functions in a…
The article explains PointNet, a neural-network architecture designed to process unordered point sets directly. Rather than converting a point cloud into a voxel grid or image, it applies shared point-level transformations and uses max pooling to create a…
This article presents an architecture for running multiple trading models across instruments and timeframes within one MetaTrader 5 expert advisor. It frames the configuration problem as a set of model, timeframe, and instrument combinations, each of which…
This installment explains how to make a market replay and simulation service more reliable when loading forex data. A configuration that loads one-minute bars before tick trades can cause the system to delete the bars when it switches price display modes,…
In this interview, Antonio Morillas discusses developing an Expert Advisor for the 2011 Automated Trading Championship. He describes a long-term trend strategy based on a moving-average slope, with buy, sell, or wait signals and a broad trailing stop. When…
This article extends standard ARCH and GARCH approaches to account for the sign of market shocks. Symmetric GARCH treats positive and negative returns of equal size alike, while the leverage effect describes how negative returns can be followed by sharper…
The article explains Differential Search Algorithm (DSA), a population-based optimizer inspired by migration. Candidate solutions move through a search space using one of several direction rules: toward a random peer, a selected top solution, a shared…
This installment describes connecting a trained classifier to MetaTrader 5 for live order execution. Predictions above or below a threshold trigger long or short trades with preset stop-loss and take-profit levels, while a cap on open positions limits new…
The article builds a Hawkes-process workflow to measure whether large market moves tend to cluster. It converts price data into event times when absolute log returns exceed a multiple of a trailing return-volatility estimate, then fits an exponential-kernel…
The article extends a liquidity-zone strategy by requiring setups to align with a trend filter based on an exponential moving average. Demand zones qualify for buy-limit orders when they form above the EMA, while supply zones qualify for sell-limit orders…
The article describes MPO4, an oscillator that estimates directional pressure by weighting each candle according to its body size relative to a recent average. Bullish and bearish candles contribute positive and negative values, respectively; the…
The article explains how to extend a simple linear regression implementation to handle multiple independent variables using matrix algebra. It introduces the design matrix, including a column of ones for the intercept, and describes transposing data,…
The article outlines a machine learning workflow that combines volume analysis with price features to predict market movements. It proposes rolling volume averages and ratios, price and volume momentum, volume volatility, and price-volume correlation.…
This article describes a graphical workflow for assembling MetaTrader 5 Expert Advisors from connected trading blocks, then generating MQL5 code. Its worked example encodes a moving average rule: buy when the shorter average is above the longer one and sell…
The article explains how MetaTrader 5 custom symbols can create controlled test environments for evaluating trading strategies. It describes a helper class that creates and deletes symbols, copies properties and tick history from an existing instrument,…
The article shows how to use MQL5’s CCanvas class to draw custom indicator graphics, focusing on transparent fills between two lines. It motivates canvas drawing as an alternative to the built-in fill plot, which does not support transparency and can blend…
The article develops a floating grid that places buy-stop orders above the current price and sell-stop orders below it, then updates the pending orders as price moves. Each position has its own take profit, while orders far from the market are removed and…
The article compares three ways to combine population-based optimizers: merge their search logic, run them in successive stages, or run them in parallel and combine their best candidates. Its worked example pairs Grey Wolf Optimization with the Cuckoo…
The article describes an end-to-end workflow that connects MetaTrader 5 data collection to Python model training and live inference. Historical bars are uploaded in chunks, enriched with technical and statistical features, labeled, and stored for training. A…
This article explains how the ALGLIB port available to MQL5 developers can support numerical work needed for dynamic hedging and multi-asset strategies. It contrasts single-window correlation indicators and hand-built calculations with tools for matrix…
The article presents an Expert Advisor design that combines a Hidden Markov Model with regime-specific Gated Recurrent Units. The HMM estimates whether conditions are ranging, trending, or unusually volatile from trend-strength and relative-volatility…
This article discusses improving a Wizard-generated, multi-signal MQL5 Expert Advisor by controlling when its signals can trigger trades. It argues that default signal modules may be technically sound yet perform poorly when allowed to vote continuously…
The document explains Mantis, a foundation model for classifying time-series patterns and market regimes. It describes splitting sequences into patches, combining local convolutional features with global attention, and using separate streams for normalized…
The article evaluates a two-sided CUSUM indicator that accumulates standardized log returns and flags a breakpoint when either accumulator crosses a threshold. It tests the Siegmund average run length formula, commonly used to estimate the spacing of false…