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 study outlines an experiment applying a Transformer model to short-horizon stock selection in China’s A-share market. Its target is each stock’s return over the next five trading days, using daily market data from 2015 through 2021. The inputs begin…
This Chinese-language excerpt summarizes a report about automatically generating trading strategies from time-series data. It frames conventional factor research, factor combinations, and rule combinations as labor-intensive manual work, then proposes using…
This document summarizes a research paper on factor timing, connecting it to market timing and factor investing. Its theoretical starting point is that an optimal portfolio corresponds to the stochastic discount factor (SDF). Under a conditional factor model…
The report summary explains a method for finding monthly indicators that may signal earnings changes in cyclical industries before standard financial statements are published. It covers real estate, autos, transport, coal, nonferrous metals, steel, building…
This Chinese stock screen combines trading activity, thematic classification, market capitalization, and fundamental filters. It seeks stocks with amplitude above 1, elevated same-day control, a robotics association, and circulating market value below 10…
This research summary treats intraday stock prices as time series rather than isolated observations. It applies empirical mode decomposition (EMD) to separate trend-like price signals from noise, then uses their relative strength to form a signal-to-noise…
This document describes an A-share stock screen that selects Shenzhen main-board shares with daily price amplitude above 1%, a nonempty outstanding convertible-bond name, positive price-to-earnings ratio below 29.01, and positive price-to-book ratio below…
This note proposes screening equities for a high dividend payout ratio in 2019, a sufficiently long listing history, and strong capital activity. It describes trading strength using measures such as turnover and relative volume, with the goal of finding…
This stock screen combines a 2019 dividend measure above a stated threshold, a 20-day moving average above the 120-day average, and a ranking by capital intensity. The moving-average comparison is presented as a way to favor stocks whose shorter-term trend…
This proposed A-share screen combines three ranking and selection inputs: descending capital intensity, descending stock popularity, and a dividend payout ratio above 25% for 2019. The document interprets capital intensity and popularity as measures of…
This weekly report reviews style-factor signals across several Chinese equity universes and summarizes recent quantitative fund performance and market conditions. It reports that price-and-volume factors, especially beta, were relatively strong in the week…
This proposed Chinese A-share screen selects stocks with turnover between 3% and 12%, excludes Beijing-listed or Beijing-based names, and uses enterprise ownership or company classification as an additional selection dimension. The accompanying discussion…
This literature summary describes applying classification and regression trees (CART) to cross-sectional stock selection. The motivating advantage is that a tree can represent nonlinear relationships and interactions among variables, which linear models or…
This weekly Chinese equity research note tracks index-enhancement portfolios benchmarked to the CSI 300, CSI 500, and CSI 1000, and monitors single-factor portfolios within those indices and a public-fund-heavy-stock universe. Its portfolio construction is…
This article outlines an approach to improving a random forest stock-selection model through factor screening and parameter experimentation. It first limits the stock universe by excluding firms under special treatment and delisted stocks. Candidate…
The document describes a Chinese stock selection rule that combines a technical screen with historical revenue growth. It selects stocks with RSI below 65, a rising MACD signal line (DEA), and 2021 revenue more than 10% above 2018 revenue. The accompanying…
This stock screen combines three filters: at least five moving averages are described as converging, price-to-earnings and price-to-book ratios fall within specified ranges, and the 20-day moving average is above the 120-day average. The first condition is…
This strategy ranks U.S. stocks by return on assets (ROA) separately within larger- and smaller-capitalization groups. ROA is defined using quarterly income before extraordinary items divided by assets from the prior quarter. Within each size group, it buys…
This report compares AdaBoost, gradient boosting decision trees, and XGBoost as tools for selecting Chinese equities from factor data. Its workflow covers feature and label preparation, preprocessing, in-sample fitting, cross-validation, and out-of-sample…
This note shows how to construct a simple stock relative-return factor using a precomputed Chinese equity dataset. It identifies one field as each stock’s daily return and another as the CSI 300 index return, then defines relative return as the stock return…
This study applies a factor-timing framework from a 2019 paper to China A-share data. It parameterizes factor weights using external variables and compares two approaches based on where the information enters: a time-series model and a cross-sectional model.…
This brief strategy description selects the 30 stocks with the smallest market capitalizations and allocates equal weights to them. It rebalances on the first trading day of each month and excludes ST-designated shares, the STAR Market, and the Beijing Stock…
This post outlines a Chinese A-share selection rule combining a technical indicator, earnings growth, and a measure described as previous-day major-holder control. Candidates must have a 14-period RSI below 65 and parent-company net profit growth above 20%…
This strategy ranks the full Chinese A-share universe using two cross-sectional signals: circulating market capitalization and five-day price momentum. It ranks each factor, adds the scores, and selects the highest-ranked 50 stocks. The portfolio assigns…