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 post asks whether a backtesting or simulation setup's commission setting includes the stamp tax charged on stock sales in mainland China. The author says that, for frequent portfolio turnover, this tax could materially reduce estimated returns compared…
The document proposes an A-share screen using daily price amplitude above one percent, a share price of 18.5 yuan, and positive institutional movement. It presents the combination as a way to select volatile stocks at a chosen price level with favorable…
The document describes an A-share stock screen that combines daily price amplitude greater than one percent, a positive weekly MACD reading, and a positive price-to-earnings ratio. It frames the conditions as a blend of volatility, short-term upward…
This proposed A-share stock screen combines a 14-period RSI below 65, a condition involving daily percentage change multiplied by a five-day large-order net-flow measure, and a current low below the prior day's low. The author frames the falling-low…
This Chinese-language post describes an equity screening rule that combines a daily price-range threshold, afternoon large-order net inflows, and a measure labeled “today’s control” above a stated threshold. Its rationale is that a wider range may indicate…
This Chinese-language post presents a short-term stock selection screen using three conditions: turnover ratio between 3% and 12%, opening price near the 10-day moving average, and intraday range of at least 1% of the opening price. The opening-price…
This A-share screening idea combines technical and fundamental filters: RSI below 65, parent-company net profit growth above 20% and no more than 100%, and upward-diverging moving averages. The article’s example implementation further screens out…
This document describes a stock screen combining three signals: a positive but limited ten-day return, the prior day's price above its 250-day moving average, and a measure of daily position increases above 5%. It interprets the position-change measure as a…
This document presents a Chinese equity screening idea focused on stocks in the metaverse industry. It selects companies with a volume ratio between 1.5 and 6, market capitalization above 200 million, and a relative-strength ranking among the top 100. The…
This note outlines an A-share selection process that filters for stocks with an amplitude above 1, excludes ST-designated stocks, and selects before 10 a.m. It then applies a five-session limit-up-style rule and ranks the remaining names by individual stock…
This note describes a stock screen that combines an intraday range threshold, at least one limit-up session in a recent lookback period, and current trading volume equal to at least 5% of circulating shares. The stated rationale is that larger ranges may…
This Chinese stock-selection post starts with three signals: daily amplitude above 1, a positive weekly MACD histogram, and afternoon large-order net inflow. Its final proposed rule adds valuation and profitability filters: price-to-earnings below 20,…
This Chinese stock-screening note describes a rule that combines daily price amplitude, a bounded turnover rate, and a ranking based on large-order net flow. Its rationale is to find shares with meaningful price movement and trading activity while using net…
This document describes a Chinese equity screening rule combining daily amplitude above a threshold, a positive weekly MACD histogram, and exclusion of stocks that hit their daily price limit on the previous day. It presents versions of the rule for a…
This research summary describes a stock-selection factor based on herding behavior in China’s A-share market. It applies the LSV model to intraday high-frequency trade records, distinguishing aggressive buyers from sellers to estimate their relative strength…
This configuration describes a Qlib workflow for training a TCTS model on the CSI 300 universe using Alpha360 features. The data span 2008 to 2020, with training through 2014, validation over 2015–2016, and testing from 2017 to mid-2020. Feature processing…
This document outlines a daily stock screen for Chinese A-shares. It selects stocks whose MACD is above zero, ranks qualifying names by market attention from highest to lowest, and requires positive net buying by major participants during the opening…
The document summarizes three Chinese equity approaches: a low-valuation growth strategy based on earnings and valuation expansion, an earnings-preannouncement strategy, and a dynamically timed reversal strategy. The reversal method waits for a market…
The document outlines an A-share stock screen combining a 3%–12% turnover range, a market capitalization below 10 billion yuan, a profitability filter, and a signal described as main-fund control on the previous day. It also provides a sample indicator…
This stock-selection idea filters for RSI below 65 and a circulating market value between 5 billion and 10 billion yuan, then ranks qualifying stocks by that day’s auction amount and selects the top five. The article frames RSI as a short-term overbought or…
This document describes a screen for Shenzhen main-board stocks combining daily price movement, opening price relative to the 10-day moving average, and valuation limits. It seeks stocks with amplitude above 1%, an open within 5% of the moving average,…
The document proposes a Chinese-equity selection screen combining prior-session price amplitude, a maximum free-float share count, and a price-position condition called “reverse covering.” Its examples operationalize that last condition as a close at or…
The article answers practical questions about machine-learning stock strategies. It says the platform separates training and test periods by time, with the test interval serving as the backtest, and describes a setup without a separate validation set. It…
The proposed Chinese equity screen selects stocks with turnover between 3% and 12%, a newly formed KDJ bullish crossover, and at least one limit-up move during the preceding month. The article frames these conditions as a combination of trading activity, a…