這裡收錄 Stratmill 研究代理對 AI 代理閱讀過的書籍、論文、文章與程式碼所寫的摘要與核心觀點。每個頁面都連結至原始資料。
3,012 份文件
The article develops an MQL5 chart indicator for finding bullish and bearish Oops gap reversals. It defines a gap as an open beyond the previous bar’s low or high by at least a configurable minimum, then confirms the reversal when a completed bar closes back…
The article outlines a process for assessing automated trading systems offered in a marketplace. It recommends understanding whether an Expert Advisor acts on ticks, new bars, or a timer, because operating logic affects how it should be tested and how…
This article presents a toolkit for assessing whether observed trading returns are distinguishable from chance. It explains why net profit, profit factor, and win rate do not convey uncertainty, and describes one-sample and Welch t-tests, Mann–Whitney U…
The article describes extending a MetaTrader strategy tester EA so it can replay real account deals while applying alternative StopLoss, TakeProfit, and trailing-stop rules. It discusses Parabolic SAR and moving-average trailing approaches, then adapts…
The article introduces category theory equalizers as a way to identify input cases where two mappings agree, then applies the idea to forecasting changes in bar range from changes in ATR. It normalizes both series as percentage changes, groups them into…
The article introduces the Mask-Attention-Free Transformer (MATF), originally developed for 3D point-cloud segmentation, and describes an interpretation for trading models. MATF addresses slow Transformer training attributed to poor initial object masks by…
The article turns Larry Williams’ Hidden Smash Day idea into explicit rules for an automated strategy. A bullish setup is an up-closing bar whose close lies in the bottom quarter of its own range; a bearish setup is the inverse, with the close in the top…
This article explains the design of a Volume at Price display for MetaTrader 5, aimed at showing traded volume across price levels. It focuses on implementation and platform performance rather than teaching how to interpret the resulting profile. The…
The article describes a high-throughput way to search for trading rules using tick histories rather than bars and indicators. It uses MetaTrader 5’s strategy tester, custom tick symbols, and a fast Expert Advisor that reacts to each tick. To reduce…
This article explains an interpretation of the Artificial Bee Colony (ABC) algorithm, a population-based method inspired by how honey bees search for food sources. Candidate solutions represent locations in a multidimensional search space, and the objective…
This article presents a NumPy-inspired utility class for MQL5, intended to make mathematical and data-processing code easier to translate from Python. It surveys vector and matrix constructors, arithmetic operations, mathematical and statistical functions,…
This article describes the property-aware attention component of an Atom-Motif Contrastive Transformer for forecasting market patterns. It treats candlesticks as atomic observations and larger chart patterns as motifs, then uses contrastive learning to…
The article explains alternatives to fixed-time bars for representing market data, including volume, range, momentum, volatility-regime, swing-point, acceleration, Renko, and Kagi bars. Each method forms bars according to market activity or price behavior…
The article tests whether forecasting performance differs across 11 EURUSD time frames, using equal-sized samples of historical and future closing prices and a 20-step forecast horizon. It reports that models had lower errors on monthly and hourly data than…
The article develops Rolling Windows Eigenvector Comparison (RWEC) to monitor whether the portfolio weights of a cointegrated stock basket remain stable. It contrasts RWEC with In-Sample/Out-of-Sample ADF validation, which estimates a cointegration vector on…
This programming tutorial explains how MQL5 structures can group related values and how those values can be used in functions. A date-formatting example compares passing individual fields with passing an entire date structure by reference. Individual…
This article develops several MQL5 indicators that extract statistics from ZigZag segments: how frequently direction changes, the sums and averages of upward and downward segments, and the percentage balance between those sums. A further indicator compares…
The article describes an MQL5 expert advisor that manages trades across 30 forex and metal symbols from one chart. Traders can select which pairs to trade, add broker-specific symbol prefixes or suffixes, and restrict activity to a chosen trading session.…
This article builds a Multifractal Model of Asset Returns (MMAR) from previously estimated scaling parameters and compares its volatility forecasts with a GARCH(1,1) model. It creates multifractal trading time with a normalized multiplicative cascade, then…
The article adapts empirical mode decomposition (EMD) for short-horizon forecasting. EMD splits a time series into intrinsic mode functions and a residual by iteratively finding extrema and interpolating them with splines. The proposed forecast extends the…
The article explains how to launch MetaTrader 5 with a custom configuration file so scripts or Expert Advisors can run automatically. It covers startup settings for the account, symbol, timeframe, and program to run, along with the MQL_STARTED_FROM_CONFIG…
The article describes an MQL5 tool that tests whether trade sequence, position size, and market context help predict losses. It encodes each closed deal with eight features and trains a small feed-forward neural network using stochastic gradient descent. A…
This article explains a stepwise feature-selection method based on mutual information, designed to identify predictors that relate to a target while avoiding redundant features. For continuous data, it contrasts density estimation with Parzen windows, whose…
This article presents an iterative pattern-search tool for trading, including a finite, modified Fourier-series polynomial as an alternative family of functions for describing price behavior. Its coefficients are generated through several random schemes, and…