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 explains how to remove stocks from a model’s predicted buy signals when they fail a chosen condition. Its example filters out stocks whose return_5 value is below 1.05, so a signal containing three names could proceed with only the two that…
This Chinese A-share screening example selects stocks using three conditions: turnover between 3% and 12%, traded volume on the buy side relative to sell-side volume above 1.3, and floating market capitalization above 10 billion yuan. The article gives…
The document presents a workflow for evaluating a stock factor with Chinese A-share data. It builds daily stock returns and industry returns, represents industry membership with indicator variables, and subtracts each stock’s industry return to form an…
This research summary presents a method for assessing analyst earnings forecast errors and whether investors give analyst consensus too much weight. Instead of fitting historical forecast errors to company characteristics, the method predicts future earnings…
This Chinese-language post describes a stock screen combining three signals: a trading range greater than the stated threshold, at least one daily gain of 10% or more during the prior 25 sessions, and a limit-up event in the preceding 25 days. It frames the…
This post presents an equity selection rule combining three signals: RSI below 65, positive large-order net inflow in the afternoon, and a shortening positive MACD histogram on a 15-minute interval. It also shows illustrative indicator and Python…
This post describes a mainland China equity screen for non-ST main-board stocks. It selects shares with turnover between 3% and 12%, a daily gain above 1%, and a price below 12 yuan. The accompanying indicator and Python examples show ways to express filters…
This stock screen selects shares with a market capitalization of at least 200 million, a 14-period RSI below 65, and a 20-day moving average above the 120-day moving average. The moving-average relationship is used as a short-term-versus-longer-term trend…
This stock screen combines three technical conditions: daily amplitude above 1%, a current high matching the highest high of the last two days, and weekly MACD above zero. The first two conditions select for recent movement and a short-term high, while the…
This reference compiles expressions for the Alpha191 stock-factor set, attributed in the document to a 2017 research report on short-horizon price and volume characteristics. The expressions draw on open, high, low, close, volume, turnover value, VWAP,…
This A-share screening rule selects stocks with turnover between 3% and 12%, a positive product of the day’s price change and super-large-order net flow, and an intraday low between 4% and 5% below the previous close. The stated interpretation is that…
This A-share stock screen combines a turnover-rate band of 3% to 12% with a newly formed KDJ golden cross, while excluding stocks that hit the daily upper price limit on the previous day. The stated rationale is to seek liquid, technically active stocks…
This post describes a narrow Chinese equity screen for beverage and alcohol import-export companies. It selects stocks whose recent trading range exceeds a threshold and whose opening price lies within a band around the 10-day moving average. The examples…
This stock selection idea screens for shares with a daily high-low range above a threshold, an upward relationship between recent prices and moving averages, trading volume above a stated level, and an opening price above the previous close. The article…
This report outlines a method for rotating among equity style factors as the macroeconomic environment changes. It proposes two signals: identify macro events historically associated with stronger performance in particular styles, and compare current macro…
This Chinese community post outlines a stock screen combining an upward-trending 30-day moving average, company characteristics, and fund strength ranked from high to low. It presents these as signals of short-term price stability, company or industry…
This Chinese-equity screen selects stocks in the metaverse theme whose volume ratio is above 1.5 and below 6, and that recorded a limit-up event within the previous month. The stated goal is to focus on recent price strength while using trading activity and…
This stock screen selects shares with a daily price range above a stated threshold, a condition described as prior-day major-player control, and a circulating share count no greater than 5.5 billion. The article interprets the range as a sign of active…
The article describes a Chinese-equity factor that looks for unusually large intraday increases in trading amount, then aggregates information around those moments into daily observations. Its rationale is that a volume surge accompanying modest, orderly…
The strategy turns conventional stock-selection rules into Boolean features for a CNN classifier. Its inputs include returns and return ranks, turnover, valuation and profitability measures, money-flow signals, volatility, technical indicators, and recent…
This stock selection idea combines a relative strength index below 65, the product of daily price change and net super-large-order volume being positive, and a price pattern described as rising from a local bottom. The rationale blends technical conditions…
This Chinese equity screening proposal combines a daily price range above 1%, a ratio formed from the previous day’s turnover rate and the current auction volume relative to the previous day’s volume between 0.5 and 2, and a positive price-to-earnings ratio.…
This Chinese stock screen combines a 14-period RSI below 65, a ranking by individual-stock heat, and a limit on the 9:25 a.m. price gain of less than 6%. The article describes the heat ranking as a way to prioritize relatively active stocks and presents the…
This Chinese equity screen combines clustered moving averages, a positive weekly MACD reading, and prior limit-up activity. The article’s final version specifies six averages—5, 10, 20, 50, 100, and 200 days—with at least six clustered, weekly MACD lines…