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.
16,761 documents
The article presents factors as the core logic of a quantitative strategy, with code serving as a way to implement that logic. It describes factors as explicit rules for selecting securities or timing trades, and argues that traders can translate subjective…
This document explains how to estimate a broker's server time zone and daylight-saving status from historical quote data. The method examines the distribution of weekly market opening times, using recurring peaks in inferred offsets to distinguish standard…
Automated trading systems translate explicit entry, exit, and money-management rules into orders monitored and executed by software. Rules can range from basic indicator conditions to custom strategies, and may specify order type and timing. The article…
This announcement describes the launch of a collaborative factor research group and outlines how participants will share and preserve their work. The organizers propose regular progress summaries, periodic research reports, and presentations, with factors…
This Expert Advisor is a configurable framework for studying trade management around a moving-average bias. It can switch between long and short positions, restrict trading to one direction, or add positions as price moves either with or against the existing…
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 utility converts Binance historical order-book depth, snapshot, and trade files into an event format used by HftBacktest. It reads CSV data, identifies or infers column headers, maps records to depth, snapshot, or trade events, and assigns exchange and…
This document describes an MQL5 Expert Advisor signal module that combines bullish or bearish reversal candlestick patterns with the Stochastic oscillator. It proposes entering long after a bullish pattern with the oscillator’s signal line below 30, and…
This tutorial shows how to turn a KDJ indicator rule into a futures trading program using the FMZ Quant C++ framework. It explains the indicator’s RSV, K, D, and J components, then uses the relationship between K and D to generate directional signals: K…
This document describes a simple automated strategy using a fractal RSI oscillator. It opens a short position when the oscillator crosses downward through an overbought threshold and opens a long position when it crosses upward through an oversold threshold.…
The document introduces a course focused on researching, backtesting, and automating option spread strategies in the domestic Chinese quantitative trading context. It says the course uses VeighNa Elite’s OptionStrategy module and presents a knowledge map…
This strategy ranks a chosen set of assets by their return over a configurable lookback period, then invests the portfolio in the strongest performer. The example universe contains a US equity ETF, an international equity ETF, and a bond ETF. It checks the…
This overview introduces Python libraries used across quantitative trading workflows. It groups tools by task: NumPy for numerical operations, Pandas for structured and time-series data, TA-Lib for technical indicators, and Matplotlib or Plotly for…
A platform forum exchange addresses whether a daily backtest that predicts a five-day return using the current day’s closing price can access that day’s prediction before the close is available. The response explains that, in the described daily setup, the…
This guide presents local checks for two common failures in factor submissions: missing values near the evaluation window’s start and look-ahead bias. For time-series factors, it recommends querying enough earlier data to cover the longest lag or rolling…
This Freqtrade strategy seeks long entries on a five-minute chart by combining trend strength, oversold conditions, and a stochastic crossover. It requires either a high short-period ADX or a higher slow ADX, a CCI reading below its oversold threshold, and…
This stock-selection proposal combines three screens: at least five moving averages clustered together, at least two limit-up sessions within a 500-day lookback, and revenue in 2021 exceeding revenue in 2018 by a stated threshold. The author’s rationale is…
This Chinese equity screening proposal combines daily amplitude above 1%, a reversal or engulfing-style candle condition, and an increase in the KDJ oscillator's K line. Its expanded version adds bullish alignment through moving-average crosses, relative…
This Chinese equity screening strategy combines three conditions: turnover between 3% and 12%, year-over-year growth in net profit attributable to parent-company shareholders above 20% and no more than 100%, and an auction-period price change greater than…
This strategy ranks commodity futures by roll return each month, buys the highest-return group, and shorts the lowest-return group. The groups are equally weighted, and positions are held for one month. The implementation calculates roll return from the…
The expert advisor compares two ways to define overbought and oversold RSI readings. Its first trigger uses fixed RSI thresholds, typically 70 and 30. Its second trigger calculates an average RSI and standard deviation from past bars, then sets upper and…
The Bago system is described as a trend-following approach built around a fast EMA crossing a slower EMA, with RSI providing a directional confirmation. Specifically, the raw signal combines a 5-period and 12-period EMA cross with a 21-period RSI crossing…
This Qlib example shows an online manager coordinating rolling model training and strategy updates. Its workflow begins by training an initial strategy set, then runs a routine that updates online predictions, prepares new tasks and models, and generates…
This short description outlines an Expert Advisor that classifies market direction from the most recently completed three bars. The trader sets a time for the analysis; the system examines the three bars preceding that time and identifies an upward or…