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.
12,226 documents
This article introduces unsupervised clustering and contrasts it with supervised classification: cluster labels are not known in advance, so judging whether a grouping is correct is difficult. The goal is to group observations so that members of each cluster…
This A-share screening idea combines daily price amplitude above a threshold, a positive weekly MACD condition, positive institutional capital flow, and a market-capitalization filter. The article describes weekly MACD as a way to capture price direction and…
This Chinese-language article describes a stock selection screen combining turnover, earnings growth, and recent price weakness. It looks for shares with turnover between 3% and 12%, year-over-year growth in net profit attributable to parent-company…
This Chinese-language document presents a screening rule for mainland Chinese A-shares. It selects stocks with a daily high-low range exceeding one percent of the high, a nonempty name for an outstanding convertible bond, and a stock code beginning with 60.…
This Chinese equity screen combines three conditions: daily price amplitude above 1, a weekly five-period moving average crossing above the ten-period average, and a positive product of price change and a large-order volume measure. The stated rationale is…
This stock screen combines a 14-period RSI threshold with an industry filter for beverage and alcohol import-export businesses and a ticker-prefix restriction to stocks beginning with 60. The document presents the criteria as a way to narrow a Chinese equity…
This article proposes a Chinese stock screen requiring price amplitude above 1, three technical indicators to produce bullish crosses, and an opening auction return between −2% and 5%. It frames the opening move as an additional filter on stocks selected by…
The post describes a proposed A-share screen combining at least five overlapping moving averages with a positive but limited ten-day price gain during 2021. Its stated rationale is to find stocks with relatively aligned averages and room for further…
This stock selection rule combines three filters: a reported measure of buying activity above 5%, the previous close above the 250-day moving average, and a market capitalization no greater than 10 billion yuan for companies without losses. The document…
The document describes a Chinese equity screening rule that combines turnover from 3% to 12%, an opening price near the 10-day moving average of closing prices, and a positive price-to-earnings ratio. “Near” is operationalized in the example as an opening…
The document proposes selecting listed Chinese main-board stocks that have turnover between 3% and 12%, belong to the robotics theme, and have circulating market value below 10 billion yuan. Within that group, it seeks stocks with evidence of institutional…
The document describes a Chinese equity screen combining three conditions: turnover between 3% and 12%, bid-side first-level volume greater than ask-side volume, and an association with the metaverse concept. It presents the conditions as a way to focus on…
The document proposes a short-term stock screen using four conditions: amplitude above 1, current volume above 10,000 lots, an opening price above the prior close, and an outside-to-inside volume ratio above 1.3. It frames range and volume as ways to find…
The document describes a stock screen that combines daily amplitude above 1, a listing history longer than one year, and more than two limit-up events in a ten-day window. The rationale is that amplitude may indicate activity, while an established listing…
This post proposes screening stocks for a large daily trading range, a recent multi-session limit-up streak, and falling closing prices across the preceding trading days. It frames the rule as a technical screen for volatile stocks whose recent price action…
This post outlines an equity screening rule that ranks stocks by capital-flow strength, favors a short moving average above a longer one, and requires repeated limit-up sessions within a recent window. It presents turnover and volume ratio as possible ways…
This note describes an A-share stock screen combining price amplitude above 1, a KDJ reading below 20, and a reversal candle pattern. The accompanying explanation treats the filters as a way to find volatile stocks that may be turning upward. It suggests…
This project overview describes a high-frequency backtesting framework built around tick-level market replay. It reconstructs order books from Level-2 or Level-3 data and models feed and order latency, along with the trader’s queue position, to make…
This note presents a Chinese A-share screening rule using price amplitude above 1, a KDJ reading below 20, and exclusion of Beijing-listed shares. It interprets the filters as seeking volatile stocks with a low oscillator reading, then suggests adding market…
This Chinese-language article outlines an equity screen using RSI below 65, circulating market value between 5 billion and 10 billion yuan, and exclusion of stocks that hit the daily price limit on the previous session. Its final stated selection logic also…
The document describes a Chinese equity screen that selects stocks with an amplitude above 1, an appearance on the previous day’s trading leaderboard, and at least one limit-up event during the prior 25 trading days. It interprets these conditions as proxies…
The document describes a Chinese equity screen that combines a daily range filter, a stock-code prefix, and a three-bar low-price pattern. It selects stocks whose high-to-low range exceeds one percent of the open, whose code begins with 60, and whose recent…
The post outlines an equity-screening approach for stocks in the metaverse industry. It combines simultaneous bullish crossovers from three technical indicators with a condition intended to identify a short-term improvement in the 15-minute MACD histogram.…
This proposed Chinese stock screen combines membership in a metaverse sector with a price-change cap of less than 6% and a rising DEA condition. The document gives formula references based on the 12- and 26-period exponential moving averages and a further…