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 stock-selection note proposes combining three filters: daily price amplitude above a threshold, a current low below the previous day’s low, and a dividend ratio above a stated level for 2019. The first two conditions identify volatile stocks making a…
This report studies whether the most unusual intraday price bar contains useful stock-selection information. It defines extremeness as the absolute distance between a bar’s return and the median intraday return, then examines the bar with the greatest…
This December 2024 market note tracks sentiment, fund crowding, and two stock-selection approaches in Chinese equities. It describes breadth and moving-average sentiment measures as elevated, with momentum indicators pointing upward. It also reports that…
The post describes a stock screen for mainland Chinese A-shares that excludes Beijing-listed shares, looks for a stacked sequence of moving averages, and requires 2021 revenue to exceed 2018 revenue by a stated ratio. The moving-average condition is…
The document translates David Polen’s bottom-up investment principles into a quantitative stock-selection approach. The original framework emphasizes financially strong companies, ample free cash flow, earnings momentum, valuation based on expected returns…
This Supermind screen selects listed Chinese stocks with price amplitude above 1, circulating market capitalization above 10 billion yuan, and a positive price-to-earnings ratio. The proposed rationale is to combine price movement, company scale, and…
This research summary examines additional ways to monitor crowding in equity investment factors. Factor crowding refers to a situation in which heavy investment in a factor may weaken its returns or make them less stable. The analysis considers asset…
This summary of a 2020 study examines equity factor strategies in China’s A-share market, where market structure and regulation can affect how familiar investment signals behave. It reports that carefully designed traditional factor strategies delivered…
The proposed Chinese stock screen combines three filters: convergence among the 5-, 10-, 20-, 60-, and 120-day moving averages; turnover between 2% and 9%; and revenue in 2021 more than 1.1 times revenue in 2018. The document frames moving average…
The document describes a Chinese equity screen that selects stocks with daily amplitude above 1%, a robotics theme, and circulating market capitalization below 10 billion yuan. It also discusses broadening the original 2021 time filter to include data from…
This platform support discussion reports sparse cross-sectional coverage for two company growth fields: year-over-year growth in free cash flow and year-over-year growth in adjusted net profit. The author says the free cash flow field has only about 800…
This Chinese stock selection proposal combines three filters: at least five moving averages converge, KDJ has just formed an upward crossover, and the stated 2019 dividend ratio exceeds 25%. The explanation interprets moving average convergence as possible…
The document proposes screening Chinese stocks for daily price range above a threshold, market capitalization below a limit, positive net profit, and a minimum period since listing. It explains these filters as a way to focus on more volatile, smaller…
The document summarizes research on a listwise learning-to-rank loss designed for constructing long-short stock portfolios. The proposed loss builds on ListMLE but gives extra emphasis to the top and bottom of the ranking, where long and short selections are…
This document describes an equity factor based on intraday volume moving through a low-to-high-to-low cycle. It smooths volume with a nine-minute neighborhood, identifies a peak and the lowest-volume points before and after it, then measures price-change…
This short strategy summary describes a quantitative stock-selection approach built with TabNet, a machine-learning model. It says the approach extracts 98 price and volume factors, trains the model on data from 2010 through 2018, and applies predictions to…
This Chinese-language post outlines an equity screening idea that combines a small market-cap ceiling, a history without losses, a weekly five-period moving average crossing above a ten-period average, and a daily increase in position holdings above a stated…
This study groups 50 Wind order-flow indicators into eight categories, then tests whether they help rank A-share stocks. Its framework combines industry-neutral portfolio sorts, cross-sectional regressions, and information coefficient analysis. The tests use…
The post proposes a Chinese equity screen that ranks stocks by market capital inflow, then selects companies below a stated market-cap ceiling that are not loss-making and have higher revenue in 2021 than in 2018. The written selection logic specifies…
The document summarizes research on weighting equity alpha factors through factor-mimicking portfolios (FMPs). It presents FMPs as an alternative representation of alpha signals under a stock covariance model, with linear combinations of factors…
The research note explains how alpha factors can be represented through factor-mimicking portfolios (FMPs) under a stock covariance model. It describes translating linear combinations of alpha factors into corresponding combinations of FMPs, then choosing…
The document proposes screening stocks using three conditions: daily amplitude above 1%, RSI below 65, and a 2019 dividend payout ratio above 25%. It combines a price-range measure and a momentum oscillator with a historical fundamental filter. The ratio is…
This document outlines a short-term stock selection screen for Shenzhen Main Board shares. It combines a daily amplitude threshold above one with a condition described as main-force control on the prior day, then filters for price-to-earnings ratios from…
This report summary describes fundamental implied returns, or FIR, as a measure of fundamental momentum intended to use more information than conventional measures. FIR accounts for lagged fundamental variables and their time trends, and can be constructed…