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 introduces perceptrons for forecasting Forex prices, describing supervised training on historical inputs and the adjustment of model weights to reduce prediction error. It discusses choices such as network size, activation functions, learning…
This article explores representing price behavior as geometric features for a perceptron rather than feeding it raw prices or oscillator values. The proposed inputs use two simple moving averages, with periods of one and twenty-four, and describe their…
This article describes a Monte Carlo style method for permuting price bars in MetaTrader 5 to examine whether an expert advisor's apparent performance depends on a particular historical sequence. It represents each bar using log differences: the next open…
The article proposes labeling machine-learning training examples from oscillator states available at the time of a trading decision. RSI, CCI, Stochastic, Bollinger Bands, and a Fourier-based method are among the examples. Values beyond overbought or…
This installment extends an MQL5 news-trading expert advisor with selectable event filters and stop-order entry settings. Traders can choose custom groups of event IDs or filter calendar events by importance, frequency, sector, type, and currency. Database…
This article outlines a screening funnel for building a market-neutral mean-reversion portfolio of Nasdaq stocks cointegrated with Nvidia. It begins with a broad broker symbol universe, applies sector and industry filters to focus on companies with plausible…
This installment in a market replay and simulation series shows how to extend an MQL5 class so it can execute queries against SQLite and retrieve results. It explains the workflow of embedding SQL scripts, creating related symbol and quote tables, inserting…
The article explains why maximum drawdown alone misses how long an account remains below its previous peak. It describes a dashboard that rebuilds an equity curve from closed deal history, then records each drawdown’s start, lowest point, recovery, depth,…
This article extends an MQL5 mouse-interaction class for chart analysis without relying on inheritance for the new functionality. It describes recording mouse position as both screen coordinates and chart time and price, converting between those coordinate…
This article describes an MQL5 indicator that visualizes how volume is distributed across price levels over a selected lookback. It retrieves candle highs, lows, closes, times, and volume through copy functions, preferring tick volume and falling back to…
This article proposes a price-movement model that estimates upward and downward step probabilities from historical price changes. It derives a normalized price speed from an average price change over a chosen interval, then uses that quantity to estimate…
This article extends an MQL5 system for displaying multiple indicators or symbols in chart subwindows. It explains how a class stores chart-object details in a structure and parses optional syntax for setting an indicator’s timeframe and pixel width. A fixed…
This article develops an Expert Advisor strategy around daily pivot levels. The indicator plots a central pivot and multiple support and resistance levels. The basic signal uses the day’s opening price relative to the central pivot and confirms entry when…
This article explains how to build a chart-based trading interface in MetaTrader 5 using chart objects arranged in a saved template. It focuses on making the interface editable through the platform’s visual tools, then loading its object definitions so an…
This article describes a custom MQL5 CFileCSV class intended to support communication between MetaTrader 5 and Python machine-learning workflows. CSV files act as a simple handoff format for transferring data to Python and returning predictions to the…
The article explains how to extend an MQL5 Expert Advisor to detect moving average crossovers, place trades under preset conditions, and send trade information to a Telegram chat. It outlines using a shorter and a longer moving average, checking for upward…
The article describes a way to examine calendar effects in financial returns using boxplots. It converts EURUSD closing prices into percentage changes, groups returns by month, weekday, and hour, and compares their distributions across a historical sample.…
The article describes a technical decision framework that combines RVGI, CCI(14), and SMA(30) to identify potential reversals. The SMA supplies price context, CCI marks overbought or oversold extremes, and RVGI crossovers confirm a momentum shift. A bullish…
The article introduces the Geweke–Porter–Hudak estimator for measuring the fractional differencing parameter d from the low-frequency slope of a log-periodogram. It distinguishes this estimate from the Hurst exponent: the measures are theoretically linked,…
The article presents the Duelist Algorithm as a population-based method for optimizing strategy parameters. Candidates compete in randomized pairwise duels; the better-performing candidate usually wins, while a luck term can affect the outcome. The algorithm…
The article explains Isolation Forest, which identifies unusual observations by repeatedly splitting feature space at random and measuring how quickly each point becomes isolated. It describes the anomaly score, the correction for tree branches that stop…
This article introduces logs as chronological records that help developers understand Expert Advisor behavior, investigate failures, monitor performance, support audits, and trigger alerts. Examples illustrate how a record can include an event description,…
This article frames raw prices and moving-average series as categories connected by three averaging functors with different periods. It calls the differences between pairs of moving averages natural transformations, tracks two such difference series, and…
The article surveys methods for smoothing price series and identifying whether observed movement departs from randomness. It discusses moving-average variants intended to reduce lag, then describes Abbe variance comparisons, signs of first differences,…