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
This article evaluates whether oil and gold prices improve forecasts of USDZAR compared with the pair’s own OHLC data. It describes exporting price histories, reversing their order into chronological sequence, aligning observations by timestamp, and…
The article explains how an MQL5 application can communicate with external quantitative software using raw TCP sockets and a native implementation of the ZeroMQ Message Transfer Protocol. It describes the request-reply pattern and the roles of protocol…
The article describes HimNet, a neural forecasting framework designed to account for differences across instruments, venues, and time periods. It represents time of day, day of week, and each series or location with trainable embeddings. Similar contexts can…
The article introduces Grey models as tools for smoothing, trend detection, channel construction, and forecasting when financial time series are short or nonstationary. It explains the classic GM(1,1) approach: apply an accumulated generating operation to…
The article explains the Labouchere cancellation staking method, a progression in which losses are added to a number sequence and the next stake is based on its remaining endpoints. Wins cancel sequence entries, so a run of wins can recover earlier losses.…
The article proposes detecting scale-varying symmetric patterns in price data through sliding-window correlation. For each starting point, it compares the first half of a window with the reversed, sign-inverted second half across a configured range of even…
The article explains how to construct a synthetic continuous futures series in MetaTrader 5 using historical data for expired contracts. It describes a custom indicator that draws candles from several futures symbols, with inputs for the number of contracts…
This article presents an MQL5 design for an automated news trader. It stores scheduled releases in a CSV file, loads them into an object-oriented Expert Advisor, and checks a momentum indicator around each release time. Within the configured window, momentum…
The article describes a pipeline that turns price changes into binary sequences, groups the bits, maps them to BIP39 words, and feeds word indices to a transformer encoder. The stated aim is to predict subsequent market sequences and inspect word patterns…
The article presents an MQL4 indicator that gathers signals from several chosen indicators across four timeframes and displays them in a chart subwindow. The table also reports how many recent bars on each timeframe have continued to show the current signal.…
The article describes Enhanced Colliding Bodies Optimization (ECBO), a population-based metaheuristic for minimizing an objective function. Candidate solutions are treated as bodies with masses based on solution quality. After ranking the population, the…
The article argues that short-term price movements can be erratic and that technical analysis built around brief periods may give a misleading picture. It frames price as an aggregate response to economic conditions and market participants’ views, which may…
The article presents a visual strategy builder for creating MetaTrader expert advisors without writing code. Users assemble blocks for indicators, prices, account data, positions, pending orders, time, logic, and trade actions, then connect compatible data…
This programming tutorial explains how to overload the index operator in MQL5 and why assignment overloading is often needed alongside it. It starts with a minimal class example, then shows how an expression using indexed assignment is interpreted as…
The article explains how MQL5 preprocessor macros can reduce repetitive code when building an object-relational mapping layer. It introduces substitutions, parameterized macros, stringification, token concatenation, and passing one macro into another to…
This article introduces Bull's Power, an oscillator attributed to Alexander Elder and calculated as the period high minus an exponential moving average. It interprets positive readings as evidence of bullish pressure and a decline toward zero as weakening…
The article explains how a single-neuron perceptron and a multilayer perceptron produce predictions, then describes how training adjusts their weights. A perceptron combines inputs with weights and a bias, applies an activation function, and can classify…
This article tests an overbought and oversold reversal pattern for baskets of currency pairs using a combined Williams %R indicator. It smooths the indicator with a longer period and examines daily, four-hour, and hourly charts. A signal is defined when the…
The article explains the Multi-future Transformer, a neural architecture for predicting multiple plausible futures for several interacting agents. It frames future uncertainty as a mixture of unimodal scene outcomes, separating distinct interaction modes…
This article describes an MQL5 tool that displays the currently active forex session as a themed world map behind a chart. It pairs map images for light and dark themes with session timing logic, chart markers, and configurable notifications. The…
This installment describes adapting an MQL5 trading interface to work with a market replay service. A server wrapper routes position queries to either the live trading server or replay data, allowing the Expert Advisor and position indicator to use the same…
The article describes a MetaTrader expert advisor that adds an on-chart control panel for a Quarters Theory price-level tool. Buttons toggle large quarter levels, small quarter levels, overshoot and undershoot areas, and trend commentary, with colors…
The article explains Bayesian Online Change-Point Detection (BOCPD), an online method that updates each bar using only current and past observations. It maintains a probability distribution over run length, the time since the latest regime break, and uses…
The article outlines a risk manager for a multi-strategy trading system, using two account safeguards: a daily loss limit that pauses trading until the next day, and a total loss limit that stops trading altogether. It defines reference values such as the…