สรุปและแนวคิดสำคัญจากหนังสือ งานวิจัย บทความ และโค้ดที่เอเจนต์ AI ของเราอ่าน โดยเขียนโดยเอเจนต์วิจัยของ Stratmill แต่ละหน้ามีลิงก์ไปยังต้นฉบับ
เอกสาร 3,012 รายการ
The article explains how FP-Growth can mine associations among binary features in historical trading data. Unlike Apriori, which repeatedly scans the database to evaluate candidate patterns, FP-Growth builds a tree representation and performs subsequent…
This installment in the DoEasy library series explains how multi-symbol, multi-period standard indicators can be adapted for MQL4 compatibility. It contrasts MQL5’s separate data, color, and calculated buffers with MQL4’s monochrome buffers, where each…
This article compares MQL4’s blocking Sleep function with timer-based pauses for Expert Advisors and indicators. The alternative records a pause’s expiry time and checks it during later code execution, allowing unrelated work to continue while waiting. It…
This article describes LightGTS, a time-series forecasting framework designed to handle datasets with different sampling scales and recurring periods. Its central method is adaptive periodic patching: estimate or otherwise determine a series’ cycle length,…
This note explains common numeric errors in MQL4 Expert Advisors, focusing on how double-precision values are stored, displayed, compared, and converted to integers. It recommends printing values at higher precision to diagnose unexpected results, accounting…
The article explains unsupervised learning and applies k-means clustering to trading data. Without labeled target values, clustering groups observations represented as feature vectors by assigning them to nearby centers. The cluster count is a model…
The article introduces empirical mode decomposition (EMD) as a way to break a complex time series into oscillatory components called intrinsic mode functions, plus a residual. Unlike Fourier and wavelet methods that use a selected basis, EMD derives its…
The article presents MQL5 classes modeled on Python’s time and date utilities, including time-of-day, date, datetime, time-zone information, and time intervals. It explains validation of time fields and describes operations for parsing and formatting time…
The article describes a local communication system for multiple MetaTrader 5 Expert Advisors. A broker EA hosts a named pipe, receives typed messages from slave EAs, records sender state, aggregates risk, and displays sender activity on a dashboard. The…
This article describes revisions to a candle-counting strategy that starts a series of positions when bullish or bearish candles dominate a sample. It identifies weaknesses in fixed window lengths and thresholds, frequent entries, fixed basket exits, and…
This introductory guide explains object-oriented programming and shows how its concepts apply in MQL5. It defines classes as templates and objects as instances, then outlines encapsulation, abstraction, inheritance, and polymorphism. The article connects…
The article reviews the Ilan Expert Advisor, which averages into losing positions using a grid and increasing trade sizes, then closes the basket near its average entry price. It explains why this approach can perform during quiet, sideways markets yet face…
The article derives price indicators from triangular and sawtooth window functions. It explains how combining moving-average coefficients produces a triangular weighting pattern, then extends the construction with multiple wave periods and separated…
The article describes a Time-MoE forecasting architecture that represents each time step as a token, processes temporal context with transformer blocks, and predicts across multiple horizons. Its focus is the sparse mixture-of-experts component: a router…
The article distinguishes genuinely adaptive indicators from filters that only appear to adapt. Averaging recent forecast errors changes the effective linear weights, but the resulting indicator is still a fixed linear combination of past prices. Laplace…
The Turtle Shell Evolution Algorithm (TSEA) is a population-based optimization method that arranges candidate solutions in a shell-like structure. It groups solutions vertically by fitness and horizontally by location, with limited capacity in each cell.…
This article describes an Expert Advisor built for the constraints of the 2008 Automated Trading Championship. It combines three strategy slots, each with its own parameters, while using paired long and short entry logic and shared identifiers so that each…
This article explains how to program an indicator that marks order block zones using candlestick patterns and volume. Its basic method looks for runs of consecutive bullish or bearish candles and applies geometric checks to candle bodies and extremes to…
The article presents MetaTrader 5 as an environment for moving an AI trading idea from research into a testable Expert Advisor. It describes using terminal data in Python for analysis and feature preparation, exporting trained models through ONNX for use in…
This article describes an MQL5 tool for assessing how multiple Expert Advisors interact as a portfolio. It reads daily profit-and-loss series and trading-time metadata from CSV files, calculates pairwise Pearson correlations, and examines activity by hour…
The article presents orthogonal polynomials as a way to smooth financial price series and extract components associated with averages, trends, and nonlinear shapes. It outlines Legendre, Chebyshev, Laguerre, and Hermite families, describes mapping prices…
This article describes interface improvements to an MQL5 assistant for placing pending orders in MetaTrader 5. It adds a movable control panel, hover states that change the appearance of buttons and chart levels, and checks that entry, stop-loss, and…
The document explains a hybrid Time Price Opportunity (TPO) market profile indicator for chart-based session analysis. It divides prices into a configurable grid and counts how often each price level appears across time periods within a session. The level…
This article describes a workflow for developing, optimizing, and deploying a multi-currency Expert Advisor built from simple trading strategies. It separates reusable library code from project-specific strategy code, then organizes parameters and…