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.
4,574 documents
This article describes a workflow for turning single-candle patterns into machine-learning inputs. It defines patterns using rules on open, high, low and close prices, including thresholds for doji bodies, shadow lengths and body size. Those rules feed an…
The article argues that written trading rules can fail under live pressure when traders override trade-count limits, profit targets, or loss boundaries. It frames discipline as a system design problem and introduces MQL5 governance code intended to monitor…
The article explains propensity scores as a way to reduce the dimensionality problem in causal matching. Rather than matching observations across many covariates directly, researchers estimate each observation’s probability of receiving treatment and match…
The article describes a pipeline for adapting a pretrained language model to forecast currency-pair direction from historical MetaTrader data. Its dataset method labels whether price is higher or lower after 24 hours, samples balanced UP and DOWN examples,…
The article explains how the Average Directional Index is built from positive and negative directional movement, true range, directional indicators, and DX. It describes smoothing the directional movement and true range over 14 periods, then averaging DX to…
This article compares forecasting price direction with predicting whether a future close will exceed the current high, fall below the current low, or remain between those levels. The latter target formalizes a classic price action idea: traders look for…
The article presents an Expert Advisor that detects potential bearish and bullish market-structure flips using swing highs and lows filtered by Average True Range (ATR). It converts ATR into a variable pivot depth, then checks whether a candidate high or low…
Alexander Topchylo describes managing Forex accounts after winning the Automated Trading Championship and explains his preference for giving investors access to a detailed, public trading history. He discusses moving toward stocks and futures and argues that…
This article describes an MQL5 expert advisor built around the Nick Rypock Trailing Reverse channel. The channel uses an Average True Range calculation and a configurable multiplier to define volatility-adaptive support levels. A transition to rising support…
This article tests a set of stochastic oscillator strategies that reinterpret extreme readings as trend signals. The baseline follows the conventional approach of buying below the oversold threshold and selling above the overbought threshold. The revised…
The article argues that decentralized broker feeds can produce materially different histories for the same forex symbol, making trading research and machine learning results difficult to reproduce across brokers. It compares four years of daily EURUSD data…
This article outlines an MQL5 expert advisor that monitors 30 forex and metal symbols from one chart. Its entry rule requires Parabolic SAR to indicate the same direction on five timeframes, from M15 through D1. It uses the M15 signal to close profitable…
The article explains how fractal dimension can describe the structure formed by simultaneous observations of multiple variables. It introduces box counting and the Grassberger–Procaccia correlation-dimension approach, where changes in estimated dimension…
The article proposes representing market activity with bars that combine price range, elapsed time, and volume distribution by price. It describes calculating a normalized volume profile, momentum from price velocity and volume intensity, and a volatility…
The article outlines an indicator that projects supply and demand zones from a selected higher timeframe onto a lower-timeframe chart. Zones are identified from a base candle followed by a larger directional impulse, with a configurable ratio used to compare…
The article describes an MQL5 Expert Advisor that places pending Forex orders through an interactive chart interface. Traders choose Buy Stop, Sell Stop, Buy Limit, or Sell Limit, enter a lot size, and adjust entry, stop-loss, and take-profit levels by…
This tutorial introduces the code structure for a basic automated trading system in MQL5, focusing on a custom class that sends orders. It explains how to create an include file, add a class with private and public members, and connect that class to an…
The document describes an MQL5 module and Expert Advisor for identifying and trading patterns from Bill Williams’ system. The Alligator’s moving-average arrangement acts as a trend filter; valid five-bar fractals and patterns from the Awesome Oscillator and…
The article describes a trading adaptation of the Hidformer multivariate time-series architecture. Its dual towers analyze temporal patterns and frequency-domain information separately, using recursive attention for sequence dependencies and linear attention…
This article proposes representing a bar’s open and close prices as Cartesian coordinates, then converting them into polar coordinates: a radial distance and an angle. It explains how trigonometric transformations and derivatives can be calculated in MQL5,…
In this interview, Automated Trading Championship participant Matúš German explains the design of his EA, which combines a moving average for trend direction with Williams Percent Range for entries and exits. Its position sizing method tracks hypothetical…
The article describes a MetaTrader 4 setup for intraday traders who want to issue order commands quickly while keeping a lightweight Expert Advisor. Control scripts pass commands and chart coordinates to the EA through terminal global variables; the EA…
The article explains how feature selection can reduce redundant or noisy inputs, simplify machine learning models, and potentially improve training efficiency and predictive performance. It groups techniques into filter methods, wrapper methods, embedded…
This article shows how to automate sequential backtest windows in an MQL4 Expert Advisor. A time-check function gates trading to selected periods, with inputs for the start date, optimization length, test length, shift between windows, and window number. The…