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 document describes an Expert Advisor that trades when a Three Line Break indicator changes color at a bar’s close. A transition in either direction—from red to blue or blue to red—triggers a trading signal. The system depends on a compiled indicator…
The article outlines a Chinese equity screening rule: select stocks with turnover between 3% and 12%, seven consecutive down sessions, and a money-flow ranking that favors stronger readings. It presents the setup as a search for possible rebounds after a…
This forum post reports that two BigQuant notebooks produce different numbers of extracted features even when no filters are applied. The author observes that one notebook appears to include Beijing Stock Exchange data while another does not, and questions…
This glossary introduces common measures for evaluating investments and trading strategies. It explains cumulative, annualized, and monthly returns; benchmark-relative performance; win rate and reward-to-risk; information ratio; standard deviation; alpha and…
This Chinese-language research summary examines whether stocks removed from the CSI 300 later rebound. It compares cumulative excess returns for additions and deletions around index changes, measuring performance from 260 trading days before a change through…
This Chinese stock-screening post combines three conditions: an RSI below 65, current volume more than 5% above the prior session, and more than two limit-up days within the past ten days. The rationale is that a moderate RSI may leave room for a rebound,…
The document outlines a trading robot that uses only the Relative Strength Index on a five-minute chart. It lists an RSI period and level alongside fixed take-profit and stop-loss inputs, and describes the approach as the author’s own version rather than the…
This indicator builds on the Didi Needles approach, which looks for crossovers or convergence among short, medium, and long moving averages. Users can adjust the moving average period, smoothing, and price input. The signals are drawn on the price chart when…
The strategy takes one long GBPJPY position each Monday, enters at a preset server-time hour, holds for twelve hours, and exits before the daily rollover. It uses no price indicators or stop loss, with spread and margin checks as its only entry guards. The…
This tutorial explains Zipline’s event-driven structure for writing and running trading algorithms. A strategy defines an initialization function for persistent state and a handler that runs on each market event, where it can read current or historical…
The document describes a strategy that ranks Chinese A-share market concepts by their recent equal-weighted stock returns, then buys stocks in winning concepts and shorts those in losing concepts. Portfolios are rebalanced monthly, with formation and holding…
This platform discussion addresses a reporting difference between older and newer versions of a StockRanker workflow. A user says the older version displayed feature importance and NDCG after a backtest, while those results were not visible in the newer…
This report summary describes a Chinese equity industry-rotation approach that scores sector conditions using financial data from regular reports, earnings forecasts, and earnings bulletins. It evaluates individual accounting measures, then combines…
This tutorial outlines a long and short strategy that uses short and long simple moving averages to identify trend changes. A bullish crossover triggers a long signal, while a bearish crossover triggers a short signal. It describes applying the approach to…
This BigQuant example builds a long-only Chinese stock portfolio from a filtered universe of main-board shares. It excludes suspended stocks and, in its feature filters, keeps non-ST stocks listed for more than a year, with positive trailing earnings and…
This expert-advisor strategy follows trend changes signaled by the TTM-Trend indicator. It checks for a colored bar when a bar closes, then opens a position; it can increase position volume when the latest deal’s profit exceeds a user-set point threshold.…
This stock-selection idea combines three conditions: daily high-low amplitude above 1%, a newly formed KDJ crossover, and an opening price at least 9.95% below the prior close, described as a prior-day 9:15 indicative match at the limit. Selected shares…
This platform discussion describes a data-ordering problem in a quantitative feature extraction workflow. The author reports that extracted rows and the original data may be separated or misaligned instead of being grouped and ordered by stock. Applying a…
This research compares ways to construct and transform analyst-consensus forecast factors for stock selection and industry rotation. It examines expected return on equity, net profit, net-profit growth, and a two-year compound-growth measure. The approaches…
The document describes a stock screen that selects securities whose codes begin with 60, whose daily amplitude exceeds 1, and whose daily decline lies between 4% and 5%. It presents the screen as a way to find volatile stocks that have fallen sharply, then…
This document describes an Expert Advisor that trades signals from the RSI_Slowdown indicator. A signal is acted on at a bar close when a colored arrow appears. The robot depends on a compiled copy of the indicator, and the instructions mention a supporting…
The document proposes a stock screen combining daily price amplitude above a threshold, a market capitalization ceiling, positive net profit, and at least five converging moving averages. It argues that clustered averages may point to a relatively stable…
This research summary tests whether machine-generated stock-selection factors add value to established manually designed factor libraries. It uses genetic programming to evolve candidate formulas from market data, then applies random forests to turn factor…
This document describes a small MT5 acceptance harness for checking an Expert Advisor’s entry-state logic against deterministic synthetic cases. Its eight fixtures cover a valid closed-bar entry, duplicate signal bar, open-bar rejection, cooldown handling,…