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.
22,592 documents
This Chinese-language post describes an equity screening rule that selects stocks with an amplitude threshold, prior-day main-fund control, and a rising DEA. It frames the conditions as combining price activity and fund-flow participation with a short-term…
This Chinese equities screening recipe combines a volatility condition, positive large-order net volume, and a long-term trend filter. It selects stocks with amplitude above 1, large-order net volume above 0.05 for at least three consecutive days, and the…
The document explains how to choose between regression and classification when building machine-learning models for stock research. A regression task predicts a continuous quantity, illustrated by forecasting a stock’s five-day return. It introduces fitting…
The document describes a stock screen for the metaverse industry that combines a newly formed KDJ bullish crossover with three consecutively declining closing prices. It outlines the intended selection logic and gives formula and Python examples for applying…
This stock-selection example filters Chinese equities by turnover, listing year, and Bollinger Band position. It targets stocks with turnover between 3% and 12%, an IPO year of 2021, and a closing price above the Bollinger middle band but below the upper…
This document describes a Chinese stock-selection screen combining turnover with year-over-year growth in net profit attributable to parent-company shareholders. It specifies turnover between 3% and 12%, profit growth above 20% and no more than 100%, and an…
The report introduces a Barra-style multi-factor risk and return attribution model for Chinese equities. Its central idea is to explain the returns and risks of many stocks through a smaller set of style factors, making portfolio exposures easier to analyze.…
This note describes a Chinese equity screen that combines amplitude above 1, a prior-day proxy for main-investor control, and return on equity above 15% in each of five consecutive years. The proposed logic aims to pair active price movement and recent…
This note presents a technical screen for Chinese stocks using daily amplitude above 1, a rounded or arc-like candle pattern, and a MACD reading below zero from two days earlier. It explains the amplitude condition as a way to find stocks with notable price…
This note describes a Chinese equity screen combining turnover, year-over-year net profit growth attributable to parent-company shareholders, and the ratio of external to internal trading volume. It selects stocks with turnover between 3% and 12%, profit…
This short BigQuant discussion asks whether factor analysis of a custom stock universe requires manually importing a data table. The response says custom feature data can instead be passed into the factor-analysis module, enabling analysis for a user-defined…
This post outlines an A-share stock screen using three conditions: a daily high-low range above a threshold, a nonempty convertible-bond name field, and a positive but capped return over ten days. It presents both an indicator-formula example and a Python…
This post describes an A-share screening recipe combining a price-range condition, exclusion of stocks marked ST, a five-session closing-high condition, and a limit on the stock’s price increase at 9:25. It also says to select stocks before 10:00. The…
The document describes a China-market stock screen that selects companies in the metaverse theme, with circulating market capitalization above 10 billion yuan and a 2019 dividend payout ratio above 25%. It defines payout ratio as dividends per share relative…
The document proposes a China A-share screening rule focused on companies classified in the metaverse industry. Its initial filters include a limit on tradable share count and a positive MACD reading. A later version adds a market-cap ceiling and selects…
This brief community post proposes adding two filters to a small-cap stock strategy: rank companies from lower to higher debt ratio and require five-year average return on equity to exceed 10%. The title advertises an annualized return of 41% and a win rate…
This BigQuant example attempts to close a stock position after its price falls more than 10% below cost, then exclude that instrument from target holdings until a cooldown expires. It tracks expiration dates in a pool, removes expired entries each day,…
This stock-selection proposal filters for main-board shares with turnover between 3% and 12%, a daily gain above 1%, and a newly formed KDJ golden cross. The accompanying Python example checks recent K and D values for a crossover and adds a J-value…
The document proposes a stock screen using three conditions: daily high-to-low amplitude above 1%, a K-line-related value below 20, and prior-day turnover above 8%. It frames amplitude as a volatility filter, the K-line threshold as a low-position condition,…
This A-share stock screen combines a volatility condition, a weekly moving-average crossover, and positive daily price action. It seeks stocks with amplitude above 1, a weekly MA5 crossing above MA10, and a daily gain greater than 1%, while restricting the…
The post describes a Chinese equity screening rule combining daily price movement, circulating market capitalization, and a rounded or arc-shaped chart pattern. Its stated conditions are amplitude above 1, circulating market value above 10 billion yuan, and…
This guide explains how BigTrader turns simulated strategy signals into live orders through a desktop trading terminal. Users connect an account and access credential, load a simulation task, review the resulting plans, adjust order sizes and times, then…
The document summarizes a report that uses a random forest model to identify rising and falling market patterns from macroeconomic indicators and market data. It describes two applications: timing exposure to the CSI 300 index and rotating among industry…
This Chinese stock-screening proposal combines three characteristics: at least five moving averages converging near one another, a preferred enterprise type, and at least two limit-up sessions within a 500-day lookback. The article interprets moving-average…