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 defines Qlib data handlers for one-minute bars, aimed at high-frequency research and backtesting. The training handler creates normalized open, high, low, close, and approximate VWAP features, along with volume features. Price features are…
This discussion compares high-frequency price and volume strategies with lower-frequency fundamental quant investing in China’s equity market. It argues that high-frequency approaches depend heavily on hardware and execution capabilities, while fundamental…
The document explains two fee mechanisms for trading on Hyperliquid: gossip priority for receiving network data and order priority for sending eligible orders. Gossip priority uses recurring Dutch auctions for IP slots; winning slots can improve peer…
This guide describes an execution module that runs algorithms in a separate process, lets users configure and monitor orders, and supports manual order routing across multiple accounts. Its five examples illustrate different execution behaviors: TWAP divides…
The document describes research that turns intraday stock volume data into factors for stock selection. It presents seven conventional volume distribution factors and six specialized ones. The methods include measuring minute volume through bucket entropy…
This document explains that a trading terminal can add quote delay beyond the network ping to the trade server. Its indicator estimates this internal lag in milliseconds by comparing the timestamp gap between successive ticks with elapsed time measured…
The document introduces microstructure segmentation: using high-frequency price and volume data to divide trading into intervals with different trading characteristics. It argues that activity levels can correspond to different price-trend behavior and…
This guide explains how to prepare tick-by-tick trades and full order-book updates for HftBacktest, noting that this level of historical data is not commonly available for free in the way daily bars are. For Binance Futures, it describes collecting raw feed…
This factor study examines whether the share of a stock’s trading volume occurring in the opening call auction contains information useful for equity selection. It builds an opening call-auction volume proportion factor from relative volume and moving…
This report introduces intraday high-frequency trading in the Chinese securities market, framing it as an attempt to capture short-lived market inefficiencies caused by investor behavior or delayed reactions to information. It defines the strategies under…
The document explains why a high-frequency trading backtest should account for delays between exchange activity and a trader’s system. It separates latency into feed latency, order-entry latency, and order-response latency, distinguishing when market data…
This tutorial outlines a workflow for modeling Chinese steel futures using high frequency market data. It starts with tick snapshots for the RB2305 contract, explains that futures may trade during night sessions, and resamples the raw observations into ten…
The document describes a low-latency container for storing a fixed number of recent market ticks. It indexes the newest observation at position zero and discards the oldest observations when new ticks push the series beyond its configured capacity. The…
This project overview describes a high-frequency backtesting framework built around tick-level market replay. It reconstructs order books from Level-2 or Level-3 data and models feed and order latency, along with the trader’s queue position, to make…
The document explains how restructuring an arbitrage scanner can reduce computation when it checks many paths across exchanges and trading pairs. It recommends separating the quick profitability check from the more detailed calculation of order prices and…
This research summary discusses high-frequency equity factors built from combinations of price and volume data to capture trading behavior. It describes two examples: an illiquidity factor adjusted for price-path changes and a factor based on aggressive buy…
This Rust component connects to a Bybit public WebSocket stream and converts incoming order book and public trade messages into internal live feed events. It subscribes to several order book depth levels and public trades for requested symbols, parses bid…
This document is a job listing for a quantitative strategy researcher in Hangzhou. It outlines research responsibilities that include building quantitative models for financial markets, studying arbitrage approaches such as statistical and event arbitrage,…
This programming demonstration shows how an MQL5 client can dispatch lengthy calculations to separate worker threads associated with chart objects. A helper header creates those objects and applies a worker expert adviser; after a task finishes, its chart…
This report summary describes a composite signal for forecasting changes in futures basis using high-frequency ETF premiums and discounts. It separates ETF observations into intraday comparisons, such as the close versus the open or the day's average, and…
This research summary describes a stock-selection factor based on herding behavior in China’s A-share market. It applies the LSV model to intraday high-frequency trade records, distinguishing aggressive buyers from sellers to estimate their relative strength…
The document describes a candlestick fitness rule intended for use in coding high-frequency trading algorithms based on population optimization. It labels a candle unfit when its body does not meet a default proportion of the relevant upper or lower wick…
This article describes using recurrent neural networks to predict the direction of the next price change from high-frequency order-book data. The study uses data from Nasdaq stocks and keeps observations where prices change, reducing the input sequence. It…
This research summary describes combining order-book data, which may reflect traders’ unexecuted intentions, with transaction-level data showing completed trades. The authors use both intuitive signal construction and machine learning to turn different types…