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 document describes a technical stock screen requiring daily price range greater than 1, a morning-star candlestick condition, and positive recent return. Its rationale is that a larger range may identify active stocks, the candlestick pattern may signal…
This note presents a Chinese stock selection rule with three filters: membership in the metaverse theme, a prior-day price above the 250-day moving average, and a prior-day signal described as main-force control. It frames the theme filter as a way to target…
This note describes a Chinese equity screen combining current trading activity, price movement, order flow, and past limit-up events. It selects stocks with turnover between 3% and 12%, a positive product of the day’s price change and net large-order volume,…
This stock screen selects for a large intraday price range, current volume above a stated threshold, a gap-up or strong opening condition, and a positive price-to-earnings ratio. The intended rationale is to combine signs of active trading and market…
This stock screen combines price location among several moving averages, a Bollinger-band position, and a recent-gain constraint. The described filters use five averages spanning short to longer horizons, place the close between the band’s upper and middle…
This stock-selection method looks for a positive MACD reading, upward short-term moving-average conditions, strong current volume, and an opening price above the prior close. The accompanying formula adds price positioning relative to a short average and a…
This stock screen combines a metaverse concept filter with an upward-sloping 30-day moving average and an intraday range threshold. The stated formula defines the range as the high-low spread divided by the sum of the high and low, with a cutoff above one…
This stock screen combines a price range filter, a weekly trend indicator, and a thematic classification. It selects shares whose daily high-low amplitude exceeds 1%, whose weekly MACD is above zero and above its signal line, and that are classified as…
This stock selection approach combines a technical filter with market size and liquidity constraints. It selects shares with RSI below 65, circulating market capitalization between 5 billion and 10 billion yuan, and prior-day actual turnover above 3% but…
This Chinese stock screen combines three conditions: daily price range must exceed one percent of the previous close, an afternoon large-order net-inflow proxy must be positive according to a stated formula, and the prior session’s high must have been below…
This Chinese equity screen selects stocks with turnover between 3% and 12%, an opening price within five percent of the ten-day moving average, and membership in the metaverse concept group. The post frames turnover and price location as technical filters,…
This Chinese equity screening idea ranks stocks by capital-flow strength and selects those with more than two limit-up sessions in the previous ten days and a positive ten-day return below 35%. The document explains these filters as proxies for investor…
This stock selection rule combines three technical filters: a 20-day moving average above the 120-day average, RSI below 65, and turnover between 3% and 12%. The moving average comparison selects stocks with a stronger shorter-term price trend than their…
The document describes a Chinese stock screen that selects shares with a daily high-low range above 1%, turnover between 2% and 9%, and a 30-day moving average that is rising versus the prior day. It presents these conditions as a technical filter intended…
This example shows a two-stage workflow for keeping predictions current with Qlib’s online model tools. First, it trains a model using a CSI 300 gradient-boosting task configuration and marks the resulting model as the online model. Second, it calls the…
The article introduces logistic regression as a binary classifier that maps a weighted combination of features to a probability. It outlines fitting the model by maximizing the likelihood of observed labels, equivalently minimizing a loss with gradient…
This post proposes selecting Chinese equities that combine a positive MACD reading, favorable company characteristics, and net buying by large orders in the afternoon. It describes the signals as complementary: MACD is used to identify positive price…
This report proposes a cross-sectional stock-selection framework that combines choices of factor subspaces, model families, and ensemble rules. Its base learners include boosted trees, ExtraTrees, random forests, Ridge regression, and Lasso regression,…
This post describes a Chinese equity screen for stocks in the metaverse industry. It requires relative volume to fall between 1.5 and 6 and uses a weekly five-period moving average crossing above the ten-period average as a trend filter. The rationale is to…
This report explores whether stock selection factors built from Level 2 transaction records can predict returns over a monthly horizon. It derives measures from trade size categories and trade direction, including the shares of trading represented by…
The document describes a stock screen combining amplitude above 1, a weekly five period moving average crossing above the ten period average, and positive returns. It presents these conditions as a way to find shares with larger price movement, an upward…
The indicator calculates theoretical long and short stop levels at a multiple of the Average True Range from the current close. It then estimates position size from account value, a base risk percentage, the stock’s beta, and the stop distance. The risk…
This document describes an equity screen for stocks with turnover between 3% and 12%, an IPO year of 2021, and a price below 12. Its rationale is to find relatively inexpensive, recently listed companies with moderate trading activity, while acknowledging…
The document proposes a short-term stock screen requiring amplitude above 1, a shrinking negative MACD histogram on a 15-minute chart, and a price below 12. It presents the shrinking histogram as a possible sign of a change in direction and uses the…