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
The document describes a stock screen combining daily price amplitude above 1%, a rising 30-day average, and ranking by stock heat. It presents amplitude as a sign of trading activity and the average’s direction as a trend filter. The heat ranking is…
The document describes a cyclically smoothed Relative Strength Index (CRSI), intended to adapt RSI signals to market cycles. It begins with upward and downward price changes, smooths them exponentially using a period derived from the estimated dominant…
The post proposes a stock-selection screen combining three conditions: price amplitude above a threshold, a rounded price shape, and circulating market capitalization in a stated band. It interprets the amplitude condition as a way to find active but not…
This Chinese equity research note proposes unexpected profitability as a source of stock-selection alpha. It measures operating profitability with return on net operating assets (RNOA), which separates operating activity from financing and is presented as…
This advanced tutorial section is intended for readers already familiar with FinRL or its market simulation companion, or who have worked through introductory notebooks. It points to a comparison of three deep reinforcement learning libraries supported by…
This stock selection rule first limits candidates to companies classified in the metaverse industry. It then requires a volume ratio between 1.5 and 6 and previous day's trading value above 60 million. The post includes an example that filters a stock list…
This stock screen combines three technical conditions: weekly price amplitude above one percent, the five week moving average above the ten week average after a bullish crossover, and MACD above zero. The accompanying example calculates amplitude from each…
This article presents a critical account of quantitative trading’s possible effects on Chinese equity markets. It argues that rapid order placement and cancellation can make displayed depth incomplete, that some funds combine stock baskets with short index…
This post outlines a Chinese stock selection method using three signals: daily amplitude above 1, a daily control measure above 21, and large-order net flow above 0.05 for at least three consecutive days. It interprets the range measure as a volatility…
This note describes a Chinese equity screen for shares with turnover between 3% and 12%, seven consecutive falling sessions, and greater volume at the best bid than at the best ask. It frames the setup as a way to find stocks that have declined for several…
This note presents a Chinese equity screen requiring turnover between 3% and 12%, a positive product of price change and net very-large-order volume, and a stock code beginning with 60. It describes these filters as a way to focus on active shares with…
This proposed equity screen combines price movement, order-flow activity, and turnover. It looks for stocks with amplitude above 1, large-order net volume above 0.05 for at least three consecutive days, and prior-day actual turnover between 3% and 28%. The…
The proposed screen focuses on companies in the metaverse sector. It selects stocks where KDJ has just formed a bullish crossover, market capitalization is below 10 billion yuan, and net income is positive. Selection is restricted to before 10 a.m. on each…
This stock screen combines daily price amplitude, weekly MACD position, and recent limit-up activity. It selects equities with amplitude above 1%, a weekly MACD reading above zero, and at least two limit-up days in the past ten days. The accompanying…
This Chinese-language post outlines a stock selection screen based on recent price movement, trading activity, and a long-term trend filter. It selects shares with amplitude above 1, a product of prior-day turnover and the ratio of current auction volume to…
This A-share screen targets metaverse-industry stocks with a newly formed KDJ bullish crossover, excludes ST-designated names, and requires five limit-up events over a five-day window. It is intended to run before 10:00 on each trading day for same-day…
This A-share screening idea selects stocks assigned to the metaverse industry that appeared on the Dragon-Tiger trading activity list the previous day and have a current-day price increase greater than 21% relative to the prior close. The article describes…
This A-share screening rule combines three conditions: a MACD signal above or crossing the zero axis, a recent high that is the highest across a two-day window, and a pre-market gain below 6% as measured around 9:25. The document provides an indicator…
This Chinese A-share screening idea focuses on stocks classified in the metaverse industry. It selects names that had at least one limit-up event in the prior 25 days and whose 20-day moving average is above the 120-day average, using the longer average as a…
The document proposes a Chinese stock screen that combines a reported daily buying-activity share above 5%, a weekly close crossing above its 30-week moving average, and a shortening MACD histogram on a 15-minute chart. The signals are intended to pair…
The document describes a Chinese equity screen combining daily price amplitude above 1%, a freely traded share count no greater than 5.5 billion, and weekly MACD above zero. It presents these filters as a way to find relatively volatile small-cap stocks with…
This screening approach targets main-board stocks associated with the robotics concept. It requires turnover between 3% and 12%, a circulating market value below 10 billion yuan, and a daily gain below 2.6% but above −5%. The article presents the combination…
This screening method selects Shenzhen main-board stocks that have been listed for more than a year, show daily amplitude above 1, and fall within specified valuation ranges: price-to-earnings above zero and below 29.01, and price-to-book above zero and…
This stock-selection method ranks shares by large-order net volume, then looks for positive readings above 0.05 across at least three consecutive days. It also requires the 20-day moving average to be above the 120-day moving average, combining a measure of…