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 compares Rust with C++, Java, Python, and Go for quantitative trading systems. It presents Rust as a way to reduce certain programming errors and support production debugging, while claiming that it offers performance close to C++, can use less…
This example demonstrates how to query tick, transaction, and order data with Qlib and resample irregular observations into minute-level series. It constructs candidate features from multiple levels of the bid and ask books, including normalized spread and…
MARE5.1 is described as a MetaTrader expert advisor for the one-minute timeframe. Its signal logic uses two simple moving averages and compares their values at the close of the current, second, and fifth bars. The document identifies configurable inputs for…
The document explains a data-processing approach for high-frequency factors that are first aggregated from intraday observations to daily values and then smoothed over multiple days. Instead of loading the full intraday history needed for the rolling window…
This note describes a single-security, multi-day approach to constructing intraday volume factors. For each trading day, the proposed measures calculate the share of full-day volume transacted within selected intervals. The intervals cover early trading,…
This programming note explains two counter patterns for an Expert Advisor that runs on each market tick. The first increments a counter on every tick, executes a chosen code block when it reaches a configurable limit, and resets it so the block can run again…
This overview describes quantitative investing as the use of rules or factors developed by analyzing historical market data. It presents broad stock coverage and repeated trading as a way to aggregate small predictive edges, and says quant strategies may…
This product description outlines a scalping expert advisor intended for major forex pairs and NASDAQ stocks. It says the EA acts using the current candle's opening price and lists configurable moving averages, trade limits, lot sizing, stop loss and take…
The document introduces volume-synchronized probability of informed trading (VPIN) as a practical way to assess order flow toxicity. It frames toxicity as informed traders’ ability to trade against liquidity providers, potentially causing market makers to…
This discussion post argues that a quantitative trading operation may need to work across high, medium, and low frequencies. It characterizes high-frequency trading as a field with relatively clear technical aims, including reducing latency and improving…
This report outlines five high frequency stock factors based on intraday price behavior, price and volume changes, returns, relationships with the market, and sequences of trades. Its main method identifies stocks whose intraday returns relative to the…
This article outlines a backtest framework for high-frequency strategies, organized around data preparation, signal generation, trade accounting, and performance reporting. It aggregates tick data into ten-second bars, derives moving averages with rolling…
This study summary examines whether index futures information can improve high-frequency technical trading rules for Chinese index ETFs. It uses genetic programming to evolve rules from five-minute price data for CSI 300 and CSI 500 ETFs and their…
This report describes combining individual-stock timing with multi-factor stock selection in a T+0 strategy. It uses deep-learning ideas to reduce a multidimensional space of parameter settings and win rates, then examines how performance changes across…
This page summarizes a research report on high-frequency factors derived from intraday trading activity. Its central idea is to select particular time windows within a trading day, calculate each window’s traded volume as a share of the day’s total volume,…
The discussion considers whether a strategy handling frequent submissions and cancellations should manage orders through the framework’s event loop or use a separate thread. The proposed approach is event-driven: submit orders, track active order identifiers…
This brief presentation listing outlines a toolkit for high-frequency factor research. Its workflow covers fast calculation of historical factor values and storage, routine batch updates, adding factors to a research database, factor analysis, and rapid…
This research note describes a stock-selection factor built from the relationship between intraday changes in net buy orders and high-frequency returns. Net buy-order changes serve as a proxy for shifts in investor buying intent, while returns represent…
The article discusses why leading Chinese quantitative private funds have become less visible among the largest shareholders of listed companies. It reports that several prominent firms and their products had appeared on such shareholder lists in earlier…
This QTPyLib example illustrates a simple event-driven futures strategy for the S&P E-mini. It counts incoming ticks and acts on every tenth tick. When flat and without a pending order, it randomly chooses a side and submits a one-contract limit order around…
This beginner overview outlines practical considerations for entering cryptocurrency markets. It recommends comparing exchanges by transparency, trading and funding fees, liquidity, volume, and asset selection, and explains the difference between maker and…
This forum post asks how to test high-frequency equity factors built from minute bars. It cites examples from a China International Capital Corporation multi-factor series: the average squared correlation between the high and low prices of 50-minute bars,…
The document outlines a basic workflow for cleaning tick-level market data before using it in strategies, backtests, or statistical analysis. It identifies duplicate records, implausible prices, out-of-order timestamps, and missing price or volume fields as…
This strategy reacts to a large size imbalance between the best bid and best ask in a limit order book. It ignores missing, crossed or incomplete book data and requires both displayed sizes to be positive. A trigger occurs only when the larger queue exceeds…