Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
3,012 documents
The article demonstrates tuning an MLP regressor for Brent oil price forecasting with the derivative-free Nelder–Mead algorithm. It defines a target using a future close, evaluates candidate settings by time-series cross-validation RMSE, and searches…
The article describes a multi-symbol Expert Advisor that adjusts risk and trade parameters according to volatility. It uses ATR to inform stop placement and classify volatility into high, moderate, and low risk tiers, with position size derived from account…
The article outlines a software architecture for running MATLAB calculations from MetaTrader 4 through MATLAB Engine, using a C++ DLL wrapper as the bridge. It organizes the work into three parts: develop the MATLAB function, build the wrapper, and write the…
The article explains an alternative chart construction method in which each bar contains a fixed number of price ticks rather than representing a fixed time interval. It distinguishes this approach from Richard Arms’s volume-weighted equivolume charts: the…
The article describes a gold-focused Expert Advisor intended to enforce prop firm rules while trading a breakout strategy. It checks available headroom against daily and overall drawdown limits before entering a trade, caps per-trade risk and loss, uses ATR…
This article turns Bill Williams fractals into visual breakout references. It distinguishes a simple penetration, where a close crosses the latest up or down fractal level, from a complex penetration, where the close crosses a line joining the two most…
The article describes FREL, a feature weighting and selection method based on regularized energy-based learning. It frames prediction as weighted nearest-neighbor classification: candidate predictors receive weights, and Manhattan distance determines how…
This article explains how to calculate a custom indicator from another indicator’s output in MQL5. Its example applies a True Strength Index calculation to RSI data and shows why the result can be missing or incorrect if the receiving indicator assumes valid…
The article presents a repeatable way to compare trailing-stop and market-exit algorithms in a trading platform. A trader marks historical buy and sell patterns on a chart, placing entries near reversals and exits after the subsequent move has had room to…
The article explains the Gravitational Search Algorithm (GSA), a population-based optimizer inspired by gravitational attraction. Candidate solutions act as agents whose fitness determines their relative masses. Agents attract one another, update their…
This interview with Automated Trading Championship participant Igor Korepin discusses his contest robot, its performance, and its suitability for live trading. Korepin says the EA’s strong early position owed substantially to luck and describes it as an…
The article presents an implementation of MASAAT, an attention-based multi-agent framework for portfolio optimization. Agents analyze price sequences at multiple scales, using directional movement thresholds to represent shifts of varying size.…
The article explains how indicator calculation choices affect the runtime of automated strategy tests and parameter optimization. For classic indicators, closed bars generally need calculation only once, while the current bar may need recalculation on each…
The article describes a basic method for walking through an HTML file in MQL4 and collecting its tag structure, with the practical aim of extracting information from a MetaTrader 4 Strategy Tester report. It explains how to read a file into a string array,…
The article presents a custom MQL5 signal that estimates the Hurst exponent with rescaled range analysis and combines it with moving-average positioning. It uses the exponent as a regime guide: values above 0.5 are associated with persistence or trending,…
The article surveys three normalization approaches for neural networks used in trading systems: standard scaling, feature scaling, and robust scaling. It discusses commonly proposed benefits of normalization, including steadier training and improved…
This article explains an MQL5 dashboard for examining pairwise relationships among a user-selected set of financial symbols. It computes correlations from price changes using Pearson for linear association, Spearman for rank-based monotonic association, or…
The article describes a custom MQL5 breakout signal that combines Disjoint Set Union (DSU) clustering with a Deep Belief Network (DBN). DSU groups adjacent high-volatility bars into time-bounded clusters using ATR expansion and Bollinger Band width as…
The article explains how online analytical processing can organize trading and optimization data as a multidimensional cube. Once records have been mapped into cube cells and aggregate values calculated, an analyst can inspect slices such as profit by…
The article presents an integrated research pipeline intended to make trading machine learning experiments reproducible and auditable, from tick data through model export for MetaTrader 5. Its data architecture keeps tick data in a session-level RAM cache…
This guide is a practical reference for porting MQL4 programs to MQL5. It maps legacy timeframe values to MQL5 timeframe constants, including the additional periods available in the newer platform, and explains that timeframe constants cannot always be…
The article describes adapting an existing MetaTrader 5 Chart Trade indicator for a replay simulator. Because the platform’s built-in one-click controls send requests directly to a live server, a simulator needs its own interface. The proposed design has the…
This article offers practical advice for customers commissioning trading software, with lessons about defining and testing strategies before automation. It warns that vague requirements, untested indicator combinations, and systems based on visual…
The article presents a generic formulation for optimizing trading systems when a platform accepts bounds on input variables but cannot directly enforce other constraints. It combines multiple performance objectives—such as return, Sharpe ratio, recovery…