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 research summary proposes stock-selection factors built from daily highs, lows, opens, and average traded prices, arguing that closing-price indicators alone miss information in price movement. It evaluates opening-price spikes, rebounds from intraday…
The document describes a method for testing factor effectiveness dynamically and selecting stocks within industries. It examines whether differences in style-factor exposure relate to differences in stock returns, then uses the results to form industry-based…
This guide describes how a BigAlpha competition participant can build equity factors using BigQuant’s DAI data engine. The specified universe is the historical membership of the CSI 1000, and the listed inputs include one-minute bars and order-book…
This proposed equity screen combines several filters: a reported increase in position holdings above 5%, a price change below 2.6% and above -5%, market capitalization no greater than 10 billion yuan, and a history without losses. The post interprets the…
This overview explains the main stages of a machine-learning workflow for quantitative investing, using a fruit-selection analogy to introduce training data, labels, features, prediction, and validation. It recommends defining the market and stock universe,…
This research summary examines stock selection factors derived from operating financial statement items, especially changes in operating current liabilities. It reports that these factors showed selection ability, with the strongest cited result for a…
This proposed Chinese equity screen combines three filters: daily high-low range above 1, return on equity above 15% in each of five years, and a turnover-weighted ratio of current auction volume to prior-day volume between 0.5 and 2. It is intended to pair…
This article describes a stock selection rule for Chinese equities. It looks for stocks with turnover between 3% and 12%, an external-to-internal trade volume ratio above 1.3, market capitalization no greater than 10 billion yuan, and nonnegative profits.…
This April 2020 industry-allocation update describes a framework that combines earnings and valuation context with macroeconomic state signals, historical pattern matching, trend measures, and public-fund positioning. Its macro component responds to weaker…
The report describes a stock-selection strategy that predicts the future usefulness of seven style factors and adjusts their portfolio weights over time. It uses historical factor information coefficients (ICs), macroeconomic variables, and market variables…
The document describes a Chinese equity screening idea combining price amplitude, ranking by net large-order flow, and a positive price-to-earnings ratio. It presents amplitude as a way to focus on more active stocks, large-order flow as an indicator of…
The document describes a Chinese equity screen that combines a daily high–low range threshold, return on equity above 15% for each of five years, and afternoon large-order net inflows. It frames the range condition as a way to select more active shares, the…
The document outlines a Chinese equity screening idea that ranks stocks by trading activity, excludes stocks whose indicated 9:25 price gain is 6% or more, and requires revenue in 2021 to exceed revenue in 2018 by a stated ratio. It explains these filters as…
This study considers whether a company’s decision to capitalize research and development spending conveys information about future project profitability. Because accounting rules allow judgment in deciding whether development costs should be capitalized, the…
This study examines whether managers of equity-focused and mixed equity funds can anticipate shifts between market styles defined by company size, and whether any apparent skill persists. It identifies funds that ranked near the top around past style…
This release overview describes VeighNa 4.0 and its new vnpy.alpha module for developing machine-learning, multi-factor strategies. The module is organized around feature datasets, model training, strategy research, workflow management, and example…
The article describes a framework that links macroeconomic and style factors with traditional asset-class allocation. It proceeds from selecting factors and estimating asset exposures to building factor-mimicking portfolios, forecasting their returns,…
The article compares long and short training windows for an AI stock selection strategy and recommends evaluating each window against a fixed validation period. In its rolling experiments, extending the sample from 2005 to 2021 changed labels, factor…
This Chinese-language post sketches a stock selection approach that ranks shares by trading activity, using volume and turnover as proxies for capital strength, and also considers share price. It proposes selecting highly ranked stocks on these measures,…
This brief installment in a multi-factor modeling series contrasts two ways of estimating factor information. It says that Barra-style models typically take factor exposures directly from fundamental or technical data, while academic approaches often…
This research summary reviews several quantitative approaches to interpreting China’s 2018 equity market. It reports historical analysis of rebounds in the CSI 1000, saying smaller-cap indexes tended to outperform larger ones during rebounds, while sectors…
This document is a brief outline of a presentation on machine learning in finance. It names four application areas: Lasso regression for commodity futures price prediction, decision trees for detecting possible financial fraud, logistic regression for…
The document introduces fund-of-funds structures and distinguishes four types according to whether the parent and underlying funds are actively or passively managed. It focuses on an actively managed parent investing in passive sector ETFs, and describes an…
The document outlines a Chinese-equity screening idea that selects stocks classified in the metaverse theme, requires a positive recent price return, and applies a threshold to a 2019 dividend-related measure. It presents the screen in both a platform…