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 post describes a Chinese equity screen that selects stocks with daily amplitude above 1%, excludes stocks that closed at the daily limit-up on the previous session, and requires circulating market capitalization above 10 billion yuan. It defines…
The essay introduces the prisoner’s dilemma and Nash equilibrium to explain why individually safe choices can produce outcomes that are worse for everyone. It then applies this framing to speculative stock trading, portraying investors as strategic opponents…
This note presents an A-share stock screen that combines daily price amplitude, a specified closing price, and year-over-year growth in net profit attributable to parent-company shareholders. The stated selection criteria are amplitude above 1%, a closing…
This note describes an A-share screen for beverage and alcohol related companies. It selects stocks with turnover between 3% and 12% and circulating market value between 5 billion and 10 billion yuan, using industry classifications to identify the target…
The document summarizes research that derives two liquidity factors from high-frequency order-book data, one associated with buy orders and one with sell orders. The factors are then aggregated to monthly frequency for use in stock selection. It reports that…
The document outlines an automated strategy that combines RSI and MACD divergence or convergence with moving averages and fractal-based trend lines. It says the EA trades using the open price of the current candle, and describes the trend line as a filter…
This edited seminar transcript surveys a Chinese quantitative research program on deep learning, then focuses on AlphaNet, a neural approach to stock factor discovery. It frames a multi-factor process as factor generation, factor combination, and portfolio…
This A-share screening idea combines a price amplitude above 1%, a prior-day condition described as institutional control, and a positive weekly WVAD signal. The post interprets these as signs of active trading, large-investor attention, and buying pressure.…
This A-share stock screen combines three technical conditions: daily price range above 1%, a positive but sub-35% return over ten days, and turnover between 3% and 12%. The rationale is to find stocks with noticeable movement and recent gains while avoiding…
The proposed equity screen selects stocks with a large daily trading range, at least two limit-up events over a 500-day lookback, and at least one daily gain of 10% or more during the latest 25 trading days. The post provides formula sketches and a Python…
This stock screen combines a sector filter for metaverse-related companies with a positive return condition and a closing price between the middle and upper Bollinger Bands. The cited indicator uses a 20-period window and two standard deviations. The…
This Chinese equity screen combines three conditions: daily amplitude above 1, a 9:25 a.m. gain below 6%, and a weekly price series crossing above its 30-week moving average. The post presents the combination as a way to consider volatility, the opening…
This Chinese equity screening post combines a 14-period RSI below 65 with three consecutive down sessions and a volume-based condition involving yesterday’s turnover and today’s opening-auction activity relative to prior volume. The intended range for the…
This Chinese-equity screening proposal combines three conditions: RSI below 65, a daily gain above 1%, and main-board listing status. It further requires large-order net buying above 0.05 hundred million yuan for at least three days. The rationale offered is…
This note describes a Chinese-equity screen for stocks in the metaverse industry. It selects shares where the KDJ indicator has just crossed upward and a five-day institutional-flow measure is positive. The approach combines a technical signal intended to…
The document describes deploying the small Kronos pretrained model on a quantitative research platform to forecast five-minute candlestick data for stocks. Kronos represents OHLCV sequences as hierarchical discrete tokens using a specialized tokenizer, then…
This indicator labels intraday candles with their sequence number from a selected market’s cash open. It converts the exchange’s local session time through UTC to broker server time, accounting for different daylight saving schedules in Frankfurt, London,…
This stock screen selects companies assigned to a metaverse industry category, with a positive recent return and five moving averages aligned at the same value. The specified averages use 5, 10, 20, 30, 60, and 120 periods, and the combined example also adds…
This stock screen combines three conditions: daily price amplitude above 1%, a listing history longer than one year, and a nonempty name for an outstanding convertible bond. The accompanying rationale treats amplitude as a sign of activity, listing age as a…
This description outlines an expert advisor that combines three moving averages with candle-based trailing stops and take-profit controls. It says the system trades using the open price of the current candle and presents major forex pairs and NASDAQ stocks…
The document describes a Chinese A-share screening rule focused on stocks associated with the metaverse theme. It combines sector membership with a circulating market capitalization threshold, current trading volume above 10,000 lots, and an opening price…
This Chinese equity screen combines a buying-pressure threshold above 5%, a weekly K-line crossing above the 30-week line, and more than two limit-up days during the previous ten days. The article interprets these conditions as signs of investor demand, a…
This research summary compares Naive Bayes, linear discriminant analysis (LDA), and quadratic discriminant analysis (QDA) as supervised methods for multi-factor stock selection. The described process extracts and preprocesses features and labels, retrains…
This Chinese equity screen combines three conditions: a 14-period RSI below 65, unchanged 30-day high and low values compared with the prior session, and an opening price less than 6% above the previous close. The article frames the morning price cap as a…