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 Chinese-language research summary describes a top-down framework for institutional fund allocation that connects macro asset views with strategy and product selection. It argues that asset allocation recommendations need to flow through to specific…
The document reviews research on whether crowded mutual fund ownership predicts subsequent stock returns. It defines stock-level crowding as active mutual fund ownership divided by average share turnover, using lagged holdings and turnover data. Stocks are…
This stock-selection method combines three filters: MACD above zero, positive trailing price-to-earnings ratio, and a closing price between the Bollinger Band middle line and upper band. The screen is intended to run shortly before each trading day ends. The…
This page presents a beginner-oriented quantitative trading curriculum for readers who may lack finance background. It points to introductory material on Python, Pandas, historical market data, financial data handling, and data visualization. It also lists…
This Chinese equity screening proposal starts with daily price amplitude above 1, a measure labeled today’s control above 21, and a concentration condition written as 70 below 20%. Its proposed refined version adds dividend yield and return on equity…
This research summary tests whether industry returns left after removing common style exposures can help rank sectors for rotation. It reports a strong difference between markets: an alpha based on the Fama–French three-factor model works for US industries,…
The document proposes a cross-sectional trading factor that combines price location, order book imbalance, trading activity, and volatility. Its price component is the percentage difference between VWAP and the midpoint, intended to reflect whether…
This overview introduces artificial intelligence as the design of systems that make decisions or predictions, including methods such as machine learning and probabilistic reasoning. It explains why these methods can help with complex tasks involving many…
This research summary reports tests of alternative and growth factors for selecting Hong Kong stocks. Of 17 alternative factors examined, most showed relatively weak selection effects; realized return kurtosis over 240 days and the ratio of recent to…
This research summary adapts the Merrill investment clock to Chinese A-shares by grouping sectors according to their economic-cycle behavior and proposed roles across recovery, overheating, stagflation, and recession. It describes two index families:…
This article explains how alternative internet and transaction data can supplement traditional equity factors. A typical fund process first defines a stock universe, filters it using industry and financial measures, scores candidates with financial and…
The article proposes a Chinese A-share screening rule that combines RSI below 65, parent-company net profit growth above 20% and no more than 100%, and signs of institutional buying. It presents the combination as a way to pair a technical condition with…
The document defines a price-based momentum factor as the 44-day average closing price divided by the current close, minus one. It compares two ways to analyze the factor: using a platform expression engine and supplying custom data. The stated test covers…
The report summary describes a two-stage stock selection process intended to enhance a fundamental factor model. First, the fundamental model creates an initial stock universe; a deep learning model then screens that set again. The stated rationale is to…
This post describes a proposed Chinese stock screen that ranks candidates by capital flow strength, requires a tradable float value above a stated threshold, and seeks companies with no losses and total market value below another stated threshold. It…
The discussion addresses a question about why a strategy cannot retrieve current factor values. The reply suggests the issue may be that some stocks or dates produce missing values, rather than that factor retrieval has failed altogether. It recommends…
This page summarizes a research paper on using intraday price and volume data to build enhancement signals. Its outline moves from converting high-frequency observations into lower-frequency features, to using genetic programming to discover price-volume…
The article describes a stock-selection screen combining a turnover-rate band with beverage and alcohol import-export classification, a robotics concept label, and a maximum circulating market value. Its accompanying discussion says the robotics theme is…
This introductory guide describes a supervised machine-learning workflow for quantitative equity strategies. It begins by defining the stock universe and target, such as a future return, volatility, or ranking, then splitting historical observations by time…
This Chinese A-share screen targets companies classified in the metaverse sector that appeared on the prior day’s exchange trading list and had a dividend payout ratio above 25% in 2019. The post frames the combination as a way to pair attention to a market…
This stock screen combines turnover between 3% and 12%, year-over-year growth in net profit attributable to the parent company of more than 20% and at most 100%, and an opening price above the 10-day moving average but no more than 3% above it. The document…
This Chinese stock-screening proposal combines a turnover band of 3% to 12%, first-level bid volume exceeding ask volume, and return on equity above 15% for each of five consecutive years. It presents the criteria as a way to find profitable companies with…
This report describes three Chinese active-equity portfolios designed to outperform active stock funds. The fund-enhancement strategy selects funds by performance tiers, reconstructs their holdings, and optimizes a portfolio while limiting deviations in…
This report tracks three Chinese active-equity strategies against an active-fund benchmark and describes how each portfolio is constructed. The fund-enhancement approach selects funds using performance tiers, builds a holdings-based universe, then optimizes…