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 reproduction of a sell-side factor based on overnight stock returns, intended to capture information advantages held by informed traders. It says the research defines the factor in stages, from a traditional overnight-return measure to…
This Chinese-language research summary examines how to use volatile price and volume factors in industry rotation strategies. It proposes using external market variables to forecast a trend factor’s returns or information coefficient, then timing exposure…
This 2020 market note reviews Chinese equity style performance and outlines a short-term outlook. It reports that small-cap reversal strengthened, value began to recover, and earnings-growth exposure showed a brief rebound. Its recommendations draw on…
This Chinese equity screen combines three conditions: daily price amplitude of at least one unit, return on equity above 15% for five consecutive years, and at least two limit-up occurrences within 500 days. The accompanying rationale treats persistent…
This research tests Chinese industry rotation signals based on cross-sectional momentum and valuation. It reports stronger industry momentum over a one-month lookback and compares industries grouped by the percentile of their current valuation relative to…
This report summary examines whether separating overnight returns from intraday returns can improve equity reversal factors in China’s A-share market. It links the market’s T+1 trading convention with a possible low-open, rising-intraday pattern that may…
This research summary argues that a fund’s track record can mix the results of successive managers, obscuring changes in style and investment approach. It proposes constructing a separate index for each manager from funds solely attributed to that manager,…
This overview explains factor investing as building portfolios around characteristics associated with returns, such as company size, valuation, dividends, and momentum. It distinguishes single-factor approaches from multi-factor combinations, broader factor…
This Chinese-language post describes a stock screen for the metaverse industry. It selects companies whose average share price is above the five-day moving average and whose return on equity exceeded 15% for five consecutive years. The stated rationale is to…
This report describes a Chinese equity risk model built on a standard multifactor framework and informed by the Barra approach. It estimates stock return covariance through factor return covariance and specific return variances. The model adjusts these…
The document presents a Chinese A-share screening idea centered on metaverse-related companies. Its stated conditions include an opening gain below a threshold at 9:25 and exclusion of Beijing-listed shares. It also discusses adding profitability and…
This post outlines an A-share stock-selection framework that uses eight cross-sectionally ranked features covering valuation, momentum and reversal, and liquidity. A LightGBM regression model predicts relative returns over a five-trading-day horizon; the…
This research summary compares ten equity valuation measures, including book-to-price, earnings-to-price, sales-to-price, dividend yield, growth-adjusted earnings multiples, cash-flow yields, and EBITDA relative to enterprise value. It describes what each…
This example outlines a long-term equity selection process inspired by fundamental value investing. A research agent reviews the latest company reports and current share prices, then selects businesses based on profitability, competitive durability, and…
This research note examines whether intraday stock market snapshots can support factors for stock selection. Snapshot data records prices, volumes, trade counts, and order-book quotes at regular intervals; the note contrasts it with trade-by-trade data and…
This overview surveys several ways to rank or select equities using quantitative models. It groups approaches into factor and risk models, statistical methods, machine learning, macroeconomic inputs, and behavioral signals. Examples include combining value,…
The article introduces random forests as an ensemble of decision trees and explains how bootstrap sampling and random feature selection create diversity among trees. It reviews classification and regression trees, impurity measures, pruning, regression…
This Chinese stock-screening post proposes selecting shares using price movement, listing age, and the dividend payout ratio for a specified historical year. It argues that a minimum price change may favor active stocks, a minimum listing history may avoid…
This report summary describes two models for China’s nonferrous metals sector: macroeconomic and industry-data timing for the sector, and multifactor stock selection within it. For timing, it uses mean t-tests to identify candidate indicators for both…
This article explains factor investing as the practice of expressing a market hypothesis in a measurable rule, rather than focusing first on programming. It distinguishes factors used to select securities from those used to time trades. To illustrate the…
The article presents factors as the core logic of a quantitative strategy, with code serving as a way to implement that logic. It describes factors as explicit rules for selecting securities or timing trades, and argues that traders can translate subjective…
This post proposes an A-share screen that begins with a reported increase in holdings above 5% and a daily price change between a 5% loss and a 2.6% gain. It then lists valuation, recent growth, and multi-year quality filters, including price-to-earnings and…
This Chinese stock-screening post proposes selecting A-share companies with daily amplitude above 1%, a robotics concept classification, and circulating market capitalization below 10 billion yuan. It also requires revenue in 2021 to exceed revenue in 2018…
This research note compares ways to estimate buyer- and seller-initiated trading. Tick-based classification uses trades relative to the prior best bid and ask, while a bar-based flow measure assigns volume according to the direction of the close-to-close…