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.
1,116 documents
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…
The article presents ACEFormer, a neural architecture for forecasting financial time series, especially noisy and irregular high-frequency data. Its pipeline first smooths inputs with convolutional filters, then applies an adaptive ensemble empirical mode…
This article describes using the Mantis time-series architecture as a market representation module within a trading agent. It processes separate market-data channels and their first differences, extracts local features with convolutions, pools them into…
This article explains how an MQL5 expert advisor can subscribe to Depth of Market updates, retrieve the current book, and process its price, volume, and side fields. The event handler receives the symbol whose book changed; initialization subscribes to book…
The article explains MacroHFT, a reinforcement-learning framework for high-frequency cryptocurrency trading. Its original design classifies fixed-length market blocks by trend and volatility, then trains specialized agents for the resulting market regimes. A…
The article presents intrinsic time as an event-based alternative to fixed calendar sampling: a clock tick is recorded when price reverses from its latest extreme by a chosen threshold. It explains how each completed move is divided into a directional-change…
The article describes an automated short-term trading approach built around Parabolic SAR and a 60-period Simple Moving Average. SAR dots above or below price are used to indicate bearish or bullish conditions, while the SMA slope acts as a broader trend…
The article presents a proof of concept for developing a C++ shared library on Linux that can be consumed by MQL5 and run in MetaTrader 5 on Windows. It explains the roles of Wine, which runs Windows applications in a Linux environment, and MinGW, which…
This article describes how an MQL5 Expert Advisor can publish structured trading signals to Apache Kafka using raw TCP sockets and a hand-built implementation of the Kafka producer protocol. It covers big-endian fields, base-128 varints with zigzag encoding,…
The article describes a generic MQL5 object pool intended to avoid repeated heap allocation and deallocation in high-frequency indicator code. At initialization, the pool creates a fixed number of payload objects and tracks available slots in an index-based…
The document discusses tick delivery for domestic commodity futures, describing a nominal feed granularity of one update per 500 milliseconds while noting that multiple transactions can occur within that interval. It argues that callback-based trading…
This document describes an MQL5 date and time library for building trading tools and Expert Advisors. It groups utilities for extracting calendar fields, converting dates, moving through periods, finding boundaries, adjusting business days, calculating…
The document outlines two high-frequency approaches for Chinese markets. In its BBO strategy, traders place small orders near the best bid and offer when the order book has a liquidity gap and large orders on both sides. The idea is to earn from incoming…
The document outlines high-frequency trading as a way to act on short-term intraday signals and accumulate small gains across trades. It groups strategies into trend-based, spread-based, and market-making approaches, and argues that their returns may…
This tutorial explains how to extend FMZ strategies beyond the platform’s standard exchange functions. It describes retrieving unfiltered REST responses, querying public endpoints, and calling signed account or order endpoints through the platform’s…
This report summary compares high-frequency factors built from minute data for stocks and futures. It groups them into return-distribution, volume-distribution, combined price-volume, order-flow, and trend-strength measures. Examples include realized…
This document develops order book imbalance as an alpha input for a crypto market-making strategy. It defines static and standardized imbalance, then compares related measures: volume-adjusted mid-price (VAMP), weighted-depth order book price, and a hybrid…
The document summarizes research using high-frequency trading data to estimate daily conditional probabilities of informed buying and selling, extending the probability-of-informed-trading approach. It applies these measures around merger announcements and…
This reference describes tick-level indicators for assessing liquidity through four dimensions: spread width, price elasticity, market depth, and concentration over the trading day. It defines relative best-quote spread as a measure that rises when liquidity…
The report introduces high-frequency trading as a way to trade on short-term intraday signals and accumulate small gains. It groups strategies into trend, spread, and market-making approaches, and argues that their returns may diversify buy-and-hold…
This indicator draws bars or candlesticks for a user-selected interval measured in seconds. Its settings include the interval and the number of days to calculate; requesting more historical days can make calculation take longer. The author says the resulting…
The article proposes a buy-side strength factor from minute-level order-book data. It combines price and displayed quantity at each of the first five bid levels, does the same for the first five ask levels, and forms a ratio of the bid-side total to the…
This guide explains how to route live trading strategy messages through FMZ. Users can enable notifications to the mobile app, verified email, or a custom webhook endpoint. For JavaScript, TypeScript, Python, Rust, and C++, a log output can be marked for…
This equity research summary describes high-frequency factors built from combinations of price and trading-volume information. It presents two examples: an illiquidity factor adjusted using changes in the price path, and a trading-behavior factor derived…