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 document surveys several cryptocurrency arbitrage approaches: buying and selling across centralized exchanges, comparing decentralized and centralized venues, cycling among assets, trading derivatives against underlying assets, and model driven…
The report studies whether intraday return distributions contain stock selection information beyond conventional daily factors. Using one-minute stock prices, it constructs factors from intraday return variance, skewness, and kurtosis, then examines…
This document explains a simplified ring buffer intended for short time series, indicator buffers, and intermediate streaming data inside trading software. It uses an unsigned 8-bit index that cycles through values from 0 to 255, so the implementation can…
This overview introduces artificial intelligence and machine learning as tools for analyzing financial data and supporting investment decisions or trading operations. It groups methods by task: supervised learning for prediction and classification,…
This research summary describes factors built from intraday snapshot data to measure the relationship between stock prices and trading volume. The reported premise is that price-volume divergence may precede higher returns whether prices are rising or…
The article challenges the idea that US regulators define high-frequency trading through a universal orders-per-second limit. It says figures repeated in public debate come from academic or market research definitions rather than an official regulatory…
The document outlines a JSON library intended for MetaTrader 5 integrations with language models and other automated systems. Its design uses a contiguous tape for parsing, direct serialization into a byte buffer, numeric parsing techniques, and an iterative…
This article describes four alleged ways quantitative traders affect or exploit short-term stock activity: creating false breakouts, pushing prices through clustered stop levels, trading aggressively near the close, and repeatedly capturing small spreads. It…
This document introduces two high-frequency trading examples: handling a dataset for reinforcement learning and predicting price trends. It explains that the dataset is represented by a Qlib DatasetH object, which can be serialized to disk and reloaded.…
This indicator description presents a one-minute scalping signal based on two modified, smoothed oscillators. Each oscillator filters the change in closing price over a lookback, then normalizes its output by a decaying estimate of its absolute peak. The…
This short reference describes a time filter for an automated trading system. The function checks whether the current time falls within a configured start and stop window, then returns a Boolean value that can gate the system’s trading logic. The example…
The document outlines a proposed high-frequency scalping Expert Advisor for gold on a one-minute chart. It tracks tick speed and deviations from a dynamically calculated VWAP, then looks for price to sweep beyond an outer deviation band and snap back.…
The document discusses converting one-minute stock data into daily observations for high-frequency price and volume factors. The example query constructs features such as volume shares across intraday intervals, price and volume correlations, correlations…
This research note examines whether intraday stock market snapshots can support factors for stock selection. Snapshot data records prices, volumes, trade counts, and order-book quotes at regular intervals; the note contrasts it with trade-by-trade data and…
This research summary examines whether intraday data can improve sector-rotation signals, focusing on realized skewness and the share of volatility attributable to downside moves. It describes constructing these measures from high-frequency observations and…
This research summary describes a stock-selection factor intended to measure herding in China’s A-share market. It applies the LSV model to intraday transaction records, classifying trades as buyer- or seller-initiated to estimate the relative strength of…
The document explains a high-frequency trading tactic that targets stale quotes left by slower market makers after a sharp price-moving announcement. It distinguishes passive limit orders, which rest in the book, from a market maker’s more aggressive prices…
This guide outlines ways to reduce read and write latency when trading on Hyperliquid. For market data, it recommends running a non-validating node with adequate compute and disk capacity, consuming node outputs directly, and constructing the order book…
This Rust example shows how to wrap HftBacktest’s local processor to add custom handling around market events and order responses. The wrapper implements the local processor interface by forwarding order submission, modification, cancellation, state, depth,…
This example generates order-latency records for a crypto trading backtest from historical feed data. It first keeps events that contain both exchange and local timestamps, then aggregates to one record per second using the last timestamps in each interval.…
This document explains a workflow for extending a MetaTrader 4 condition scanner. A new scan is assigned an identifier, then organized into custom indicators, chart and panel indicators, and an include file that returns a value for each tested bar. The…
The document describes a MetaTrader 4 class for analyzing incoming tick prices. Its listed measurements include elapsed time, distance traveled, movement speed, acceleration, direction, and an estimated remaining path based on acceleration. An example expert…
This strategy starts by placing buy and sell limit orders around the best bid, then follows whichever side fills. After a fill, it cancels opposing and profit-taking orders and adds another same-direction order at a wider, position-dependent grid interval.…
The document outlines an event-driven trading system designed for cryptocurrency strategies, including market making and higher-frequency activity. It describes an asynchronous event loop for processing work and a message queue that connects separate market…