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
This MetaTrader expert advisor trades using two moving averages and lets the user choose between fixed-lot sizing and sizing based on a percentage of free margin. Stop loss, take profit, and trailing stop features can each be enabled or disabled. A…
This screening concept ranks Chinese stocks by capital strength, using measures such as trading value or turnover, then applies a minimum company scale and a revenue growth filter. The specified comparison checks whether revenue in 2021 exceeded its 2018…
This stock-screening proposal combines three technical conditions: amplitude above a threshold, a shrinking negative MACD histogram on a 15-minute chart, and a weekly relationship involving the 30-week moving average. The intended rationale is to find…
This note offers practical guidance for developing and operating AI-driven equity strategies. It recommends judging possible strategy failure by comparing live maximum drawdown with the largest drawdown observed in a long backtest that spans a full bull and…
The RSRS approach models changing support and resistance through the relationship between recent daily highs and lows. Rather than treating support or resistance as fixed price levels, it uses the regression slope to represent their relative strength. The…
This monthly review assesses equity factors using information coefficients and market-neutral long-short returns. Its February 2018 discussion reports stronger results for profitability and growth measures, including return on assets, return on equity,…
This indicator tool groups historical outcomes by the rounded value of RSI, Stochastic, Williams %R, or ADX, then displays results across indicator values in a scatter chart. For each value it separates observations by whether the signal candle closed up or…
This report examines price momentum in Chinese equities and organizes possible improvements into a two by two framework: refining the price or return used to measure momentum, and incorporating the path of prices or returns during the formation period. It…
This QuantStats tear sheet reports a short backtest of a strategy labeled as a Nancy Pelosi trading bot and compares it with SPY. The displayed test period runs from January 19 to February 12, 2026, using Yahoo data. The report lists returns, risk measures,…
This tutorial walks through a machine learning workflow for a virtual stock trend prediction competition using BigQuant. It covers importing competition data, converting CSV files to HDF, inspecting data, selecting input features, extracting derived…
The strategy tracks the daily price difference between continuous WTI and Brent crude futures and compares it with a 20-day simple moving average. When the spread is above its average, it takes positions intended to profit from a decline toward that…
This document describes a MetaTrader 5 version of the FX Sniper Ergodic CCI indicator that lets the user choose the indicator's calculation timeframe through an input parameter. The example default is a four-hour period. In practical terms, the setting…
This Chinese-language post presents a stock screen for names classified in a metaverse theme. It combines an opening move threshold, described as the 9:25 gain being below 6%, with a price-change band: above a 5% loss and below a 2.6% gain. The post supplies…
This report summary describes a method for improving return on equity as a stock-selection factor. Starting from quarterly ROE, it derives four features from its time series: year-over-year earnings comparison, stability, persistence, and growth. The…
The document describes an Expert Advisor that takes signals from the XHullTrend_Digit indicator. A signal is generated when a bar closes and the indicator cloud changes color. The compiled indicator must be installed in the terminal’s indicator folder for…
This overview discusses how machine learning can address high-dimensional and nonlinear return-prediction problems that strain conventional econometric methods. It frames the challenge through empirical asset pricing, including factor models, a proliferation…
This MetaTrader 5 expert advisor uses changes in the CandlesticksBW indicator’s candle color as trend-change signals. It evaluates signals when a bar closes and lets the operator restrict trading to a selected daily time window. The documented defaults allow…
This document outlines a Chinese equity screen that combines a daily price-range threshold with a reversal or engulfing-style candle pattern, using 2021 data. Its stated logic selects stocks whose high-to-low range exceeds one percent and that show a recent…
The document describes a cross-market futures reversal strategy. It groups contracts by recent changes in trading volume and open interest, then selects contracts in the high-volume, low-open-interest group. Within that subset, the stated method goes long…
This document describes an Expert Advisor that trades from the i-CAi_StDev indicator. It opens a position when a colored indicator point appears at a bar’s close, then exits when the indicator changes direction against the open position. The system depends…
This report examines whether analyst expectations data can help rank industries for rotation. It groups signals into analyst coverage and forecast disagreement, the direction of earnings revisions, and the size of forecast changes. Coverage and disagreement…
This Chinese-language tutorial proposes testing an “upward continuation” candlestick pattern and using it to screen stocks. The method starts with a reference chart, searches historical price data for patterns with at least 0.8 similarity, then measures…
The post proposes screening stocks for amplitude above a threshold, an average price above the five-day moving average, and a negative MACD reading from two days earlier. It frames the combination as a way to find shares with volatility, price strength…
This tutorial outlines a TensorFlow LSTM workflow for forecasting stock or index returns. It recommends transforming closing prices into returns, then arranging recent observations into sequential input groups with the next observations as prediction labels.…