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 document describes a stock screen combining three conditions: amplitude above 1, a shortening negative MACD histogram on a 15-minute chart, and positive net buying attributed to major participants during the auction. The stated rationale is to find…
This note proposes selecting Chinese stocks associated with both the metaverse theme and beverage or alcohol import-export businesses, subject to prior-day actual turnover between 3% and 28%. It frames thematic exposure as a possible source of growth and…
This note describes a simple China A-share stock screen combining a turnover range of 3% to 12%, market capitalization below 10 billion yuan, no reported loss, and a closing price of 18.5 yuan. It presents the screen as a way to identify candidates for…
This document presents a daily stock-selection screen based on three price conditions: an intraday range greater than 1%, a reversal or engulfing-style candle pattern, and a daily return between -5% and 2.6%. It characterizes the idea as a possible…
This document describes a simple daily stock screen combining a turnover-rate band, the sign of a price-change and large-order-flow product, and a comparison of consecutive daily lows. It selects stocks with turnover between 3% and 12%, a positive product of…
The post proposes a stock screen requiring MACD above zero, positive trailing price-to-earnings, and previous-day turnover above 60 million. It says selection is performed before 10 a.m. and suggests sorting qualifying stocks by turnover. The stated…
The proposed stock screen combines three signals: intraday amplitude above a stated threshold, ranking among the top five by that day’s auction amount, and short moving averages ordered above longer ones. The accompanying rationale treats amplitude and…
This research note describes two revisions to AlphaNet, a neural model that learns stock selection factors from raw price and volume data. Version two adds ratio features, replaces pooling and dense layers with an LSTM to capture temporal patterns, and gives…
The document presents a Chinese equity screening rule: select stocks whose codes begin with 60, whose turnover rate falls between 3% and 12%, and that did not hit the upper price limit on the previous day. It also includes a Python example that retrieves a…
This document presents a Chinese stock-selection screen using price amplitude, a concentration-related measure, and moving-average direction. Its initial description calls for amplitude above 1%, a concentration condition, and an upward 30-day average. A…
This document describes a Chinese equity screening rule that selects metaverse-related stocks when an institutional-flow measure is positive and the prior day's actual turnover falls between 3% and 28%. It presents the conditions as a way to combine industry…
This Chinese stock-screening proposal combines an amplitude filter, simultaneous bullish crosses among three moving averages, and a condition that the prior close be above its 250-day moving average. It presents the setup as a way to find stocks with recent…
This Chinese equity screen looks for stocks in the metaverse sector that closed above their 250-day moving average on the previous day and had at least one limit-up event during the prior month. The long moving average acts as a price-trend filter, while the…
This stock screen combines three filters: a daily high-to-low range above 1% of the previous close, a ticker beginning with 60, and a prior-day main-fund flow condition. The accompanying indicator formula and Python example express the flow condition as a…
This Chinese equity screening rule selects stocks from 2021 with a 9:25 a.m. price rise below 6%, then ranks them by capital strength from highest to lowest. The stated goal is to favor the highest-ranked names after applying those two filters. The document…
This Chinese-language post outlines an equity screen requiring price amplitude above 1, a high equal to the highest high of the current and previous day, and at least one limit-up event during the prior 25 days. It frames the conditions as a way to find…
This Chinese-language post describes an equity screen combining a volatility condition, at least one daily gain of 10% or more in the prior 25 trading days, and a stock concentration measure below 20%. It also proposes adding fundamental and valuation…
This tutorial shows how to build a long-only moving average crossover strategy by combining reusable strategy components from a Python backtesting library. It turns the relationship between a short and a longer moving average into entry signals, allocates…
This stock selection rule combines a turnover range of 3% to 12%, three consecutive declining sessions, and a reported control ratio above 21%. The article frames the high control ratio as a sign of concentrated holdings or buying by large investors, while…
This document proposes a stock screen requiring a daily price amplitude above a stated threshold, MACD above its zero line, and membership in the metaverse concept group. It presents the concept theme as an additional selection dimension and gives indicator…
This document outlines an equity screen combining a metaverse industry classification, an arc-shaped price pattern, and shortening green bars in a 15-minute MACD histogram. Its accompanying formula also applies price-range and moving-average conditions,…
This note describes an A-share screening approach that combines a daily high-low range greater than one percent, at least one limit-up session during the previous 25 days, and current volume above its 21-day average. The accompanying Python example adds a…
This meetup page collects questions about quantitative trading on the BigQuant platform. Topics include searching for holding-period parameters in a default stock-ranking template, defining reusable Python modules, and building a workflow for developing…
This note presents an A-share stock screen combining a daily trading-range threshold, at least one limit-up session in the prior 25 days, and current volume above its 21-day average. Its sample formulas also add a condition that the current low is close to…