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 document summarizes a research report on recurring changes in traditional equity factor performance, including value, momentum, low volatility, and quality. Its central idea is to identify factor regimes from the factors’ own return histories, since the…
This Chinese-language research summary reviews interim earnings forecasts for ChiNext, a Chinese growth-stock board. It reports that 703 listed companies had published forecasts and evaluates profit growth using free-float market-cap weighting. The analysis…
This study proposes a monthly stock-selection factor based on how prices respond when individual stocks experience unusually large intraday increases in trading volume. It identifies spikes by comparing each minute’s volume increase with that stock’s daily…
The proposed Chinese equities screen narrows the universe to companies classified in the metaverse industry, then looks for an opening price near the ten-day moving average of closing prices. The article describes this proximity as a way to find stocks with…
The document proposes a Chinese equity screen that selects stocks with an amplitude above one, ranks them among the top five by the day’s auction amount, and requires daily MACD to be positive. It explains these filters as a combination of price movement,…
This summary of a 2018 brokerage study examines whether capital-flow measures can help anticipate shifts among equity investment styles. It argues that raw fund-flow observations may add little beyond price and volume because those variables move together,…
This study examines whether futures-curve shape can rank commodity markets. It explains backwardation, where deferred contracts are cheaper than nearer ones, and contango, where they are more expensive. The article connects these patterns to supply, demand,…
The strategy ranks equities by a short-activity measure and forms a monthly long-short portfolio. It sorts stocks into deciles using short interest relative to shares outstanding, buys the lowest-ratio group, and shorts the highest-ratio group, with equal…
The post contains a proposed monthly China A-share industry-rotation backtest. It ranks second-level industries by where current price-to-earnings ratios sit within their own rolling 60-session ranges, then selects six industries with the lowest relative…
This research digest summarizes two distinct topics. For multi-factor index construction, it contrasts a top-down approach, which combines single-factor indexes using assigned proportions, with a bottom-up approach, which optimizes holdings to increase…
This forum post describes an exploratory factor-construction exercise in the Chinese A-share market. The author says a small modification to a factor combination produced strong short-side results, then describes a revised version that removed the short…
The document describes a stock-selection rule for Chinese equities that combines a 14-period RSI below 65, first-level bid volume greater than ask volume, and return on equity above 15% in each of five consecutive years. It frames the technical conditions as…
The document outlines three ways to explain portfolio results: style analysis using return regressions, benchmark-relative return decomposition, and multi-factor attribution. It describes the data each approach needs, including portfolio and benchmark…
This report summary describes revisions to AlphaNet, a neural network that learns stock-selection factors directly from raw price and volume data. AlphaNet v2 adds six ratio features, replaces pooling and dense layers with an LSTM to capture temporal…
This document describes an annual equity screen combining a price-range condition, a measure labeled institutional accumulation, and a requirement for sustained return on equity above a stated threshold. It further limits the universe to stocks in the upper…
The document summarizes a study of four MSCI smart beta equity indexes—value weighted, equal weighted, momentum, and minimum volatility—against a market-cap-weighted benchmark. Using monthly returns over 1999–2014, the study applies principal component…
The document explains a cost-concentration measure for the estimated purchase costs of a selected share of investors’ holdings. It defines the measure as the difference between the upper and lower bounds of that cost interval divided by their sum. A narrower…
This proposed Chinese equity screen combines three conditions: daily price amplitude above 1, prior-day trading amount above 60 million, and year-over-year net profit growth attributable to parent-company shareholders above 20% and no more than 100%. The…
The report reviews the development of Smart Beta index funds in China and compares single-factor strategies in A-shares with counterparts in the US. It describes a Chinese market where offerings are relatively early-stage, commonly single-factor, and held…
This document proposes screening Chinese equities by daily turnover, circulating market value, and shareholder concentration. Its stated selection rule keeps stocks with turnover between 3% and 12%, circulating value between 5 billion and 10 billion yuan,…
The article proposes screening equities for a daily high–low range greater than one, return on equity above 15% for each of the prior five years, and an upward-moving average pattern. It frames the range condition as a way to find more active shares, the ROE…
This strategy ranks stocks across mainland China’s A-share market using a small-cap factor and a five-period momentum measure. It combines the market-cap rank with momentum into a composite score, selects the top 50 names, and assigns equal weights. The…
This strategy ranks stocks across mainland China’s A-share market using a small-cap factor and a five-period momentum measure. It combines the market-cap rank with momentum into a composite score, selects the top 50 names, and assigns equal weights. The…
This Chinese-language article presents an annual stock-selection screen combining three conditions: amplitude above a threshold, a change in a proxy for institutional buying activity, and a positive daily MACD reading. At the start of each year, it further…