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.
4,194 documents
This note describes a Chinese equity screening rule combining a relative-strength index below 65, revenue in 2021 more than 1.1 times 2018 revenue, and a 2019 dividend payout ratio above 25%. The intended rationale is to pair revenue growth with a dividend…
The post proposes a Chinese stock screen combining price amplitude, prior-day actual turnover, and time since listing. It selects stocks with amplitude above 1, turnover between 3% and 28%, and a listing history longer than one year. It includes sample…
This note outlines a stock-selection approach combining a historical dividend condition, a nonempty convertible-bond short name, and moving-average analysis. The initial specification mentions at least five moving averages and a 2019 dividend ratio above…
This report summary describes ways to derive equity selection factors from the distribution and time patterns of individual trade amounts within each minute. Proposed statistics include quantiles, standard deviation, skewness, and kurtosis. It also discusses…
This note proposes screening Chinese equities for companies with market capitalization below 10 billion yuan, scale above 200 million yuan, no losses, and at least five moving averages converging near the closing price. It suggests using 5-, 10-, 20-, 50-,…
This document outlines an equity screen using three criteria: at least five moving averages converging, a listed float market capitalization above 10 billion yuan, and a 2019 dividend payout ratio above 25%. It frames moving-average alignment as a sign of…
This stock-selection post proposes filtering for shares with MACD above zero, rising short-term averages, membership in a robotics-related concept group, and circulating market value below a stated cap. It frames positive MACD and rising averages as signs of…
This research summary compares 17 machine learning approaches with conventional linear methods for predicting stock excess returns from 51 alpha factors. It describes splitting the prediction into two parts: an AR(1) forecast for return dispersion and a…
The document describes a monthly equity strategy based on market capitalization. At each month end, it ranks eligible stocks from smallest to largest by market value and buys the ten smallest. The portfolio holds those selections for the following month,…
This review summarizes research applying machine learning to monthly and annual returns for Chinese A-shares. The study combines stock characteristics, macroeconomic variables, and industry indicators, then compares linear models, tree methods, and neural…
The document describes a Chinese-equity screening rule based on turnover, circulating share count, circulating market value, and a positive price change. Its final rule specifies turnover from 3% to 12%, circulating market value above 100, circulating shares…
This example proposes screening stocks using a price amplitude threshold, a dividend-and-bonus ratio above 25% based on the previous close, and a recent sequence of limit-up closes. It provides a formula sketch and a Python-style outline for calculating…
This stock selection example combines a daily price range threshold, return on equity above 15% for five consecutive years, and simultaneous upward crosses of the five-day moving average over the ten-, twenty-, and thirty-day averages. Its final proposed…
This screen targets Shenzhen Main Board equities using a combination of price activity, trading flow, and valuation. Its stated criteria include daily amplitude above 1%, ranking by large-order net buying, a positive price-to-earnings ratio below 29.01, and…
This Chinese equity screen combines daily price movement, company profitability, market capitalization, and MACD. It initially selects companies with daily high-to-low movement above 1%, market capitalization below the stated ceiling, positive net profit,…
This stock screen selects equities with MACD above zero, a positive price-to-earnings ratio, and a high ranking for net main-fund inflows on the previous day. The note frames these conditions as indicators of upward momentum, positive earnings valuation, and…
This document outlines an annual stock selection approach that combines a positive MACD signal with high stock heat and a record of strong profitability. It proposes screening after annual reports are published, requiring return on equity above 15% in each…
This assignment analyzes how a stock selection strategy’s exposure to market styles changes over time, then outlines a framework for rotating among factor strategies. The initial analysis uses a small-capitalization selection factor and compares strategy…
This document describes a cross-sectional momentum strategy for equity mutual funds. It first limits the universe to no-load funds, then ranks eligible funds by their trailing six-month returns. The portfolio holds the top decile, equally weighted, and…
The document summarizes research on shared movements across commodity markets. It reports that commodity return fluctuations often move together and that a common factor explains a substantial portion of their variation. The factor is closely associated with…
This research summary proposes an information-distribution uniformity factor, UID, based on the idea that uneven arrivals of information create changes in share-price volatility. It uses intraday stock data to calculate daily high-frequency volatility, then…
This proposed Chinese A-share stock screen combines a turnover-rate band of 3% to 12%, exclusion of Beijing-listed shares, and a holder-concentration condition described as concentration below 20%. The article’s rationale is that lower concentration may…
This article examines how the length of a training window affects an AI stock selection model. It compares long historical samples with shorter rolling samples and recommends checking each choice against a held-out backtest period. In the author's…
The article reviews research on salience theory in equity pricing. Investors are proposed to overweight unusually prominent past returns relative to the market: strong standout gains can attract demand and raise prices, while conspicuous declines can depress…