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 summary of a research report examines the Chinese New Year calendar effect in mainland Chinese equities and how it relates to common quantitative factors. It reports that the broad market historically had an unusually favorable risk-adjusted profile…
The document explains mean reversion as the tendency for prices or business performance to move back toward a longer-term center after unusually strong or weak periods. It connects this idea to contrarian investing: investors may examine past laggards as…
This study examines whether the number of executions recorded in tick data can improve a conventional reversal factor for Chinese A-share equities. It divides the traditional factor using trade-count information and proposes a refined reversal signal. The…
This Chinese equity screening idea ranks stocks by capital-flow strength and selects those with more than two limit-up sessions in the previous ten days and a positive ten-day return below 35%. The document explains these filters as proxies for investor…
The article introduces logistic regression as a binary classifier that maps a weighted combination of features to a probability. It outlines fitting the model by maximizing the likelihood of observed labels, equivalently minimizing a loss with gradient…
This report proposes a cross-sectional stock-selection framework that combines choices of factor subspaces, model families, and ensemble rules. Its base learners include boosted trees, ExtraTrees, random forests, Ridge regression, and Lasso regression,…
This report explores whether stock selection factors built from Level 2 transaction records can predict returns over a monthly horizon. It derives measures from trade size categories and trade direction, including the shares of trading represented by…
This document describes an equity screen for stocks with turnover between 3% and 12%, an IPO year of 2021, and a price below 12. Its rationale is to find relatively inexpensive, recently listed companies with moderate trading activity, while acknowledging…
This document outlines a Chinese equity screen using three conditions: price amplitude above 1, a 9:25 price increase below 6%, and recent revenue at least 1.1 times the 2018 revenue figure. It frames the revenue comparison as a growth filter and combines it…
This document describes an A-share stock screen combining a 14-period RSI below 65, year-over-year net profit growth above 20% and no more than 100%, and a 9:25 price increase below 6%. Its accompanying query example adds positive net profit, a free-float…
This Chinese A-share screen selects stocks with MACD above zero, a qualitative business-character assessment, and a daily price change within a specified range. The article frames the rule as combining a technical momentum condition with a basic…
This guide explains the workflow for a BigQuant contest focused on constructing 15-minute factors from three-second stock snapshot data. Participants are asked to write factor logic without using model-generated factor synthesis. The platform provides…
This Qlib configuration trains an ADD model using a GRU base model and Alpha360 features to rank CSI 300 stocks. Features are robustly normalized and missing values are filled; labels are cross-sectionally rank-normalized after missing labels are dropped.…
The study tests institutional ownership data as a quarterly stock-selection factor in Chinese equities. It measures ownership share, the number of institutions holding a stock, and average holdings per institution as a proxy for ownership concentration. For…
This research digest summarizes two finance topics. The first reviews competing claims about the size effect, the long-discussed idea that smaller companies have higher average returns than larger ones. It says the underlying study uses simple tests and…
This overview describes a practical Python workflow spanning data collection, database access, and machine-learning, deep-learning, and natural-language-processing tools. Its investing example uses traditional factors measured over rolling 12-month windows…
The document outlines how sequence learning can fit into a conventional quantitative investment process: feature extraction, individual asset return prediction, portfolio construction, and trade execution. It describes using price and volume measures,…
This weekly factor report describes two forms of diagnostics for the ten highest-ranked anonymous ModelScore factors: average style exposures estimated through daily multivariate regressions, and average industry-level Rank ICs measuring the cross-sectional…
This document poses a model-design question: whether the number of input factors in a StockRank model relates to the number of leaves per tree or the total number of trees, and whether there are useful rules of thumb for choosing these quantities. It…
This Chinese-language post describes a stock-selection screen combining three filters: membership in the metaverse theme, positive institutional activity, and return on equity above 15% in each of five consecutive years. It frames the theme as a…
This Chinese stock-selection note describes a screen for companies classified in the metaverse sector. It keeps stocks with a circulating market value above 10 billion yuan and a circulating share count no greater than 5.5 billion. The stated rationale is to…
This Chinese stock screen selects shares with an amplitude above 1, a dividend payout ratio above 25% in 2019, and positive weekly candlesticks in consecutive weeks. The article interprets the price-range condition as a volatility filter, the historical…
This summary reports tests of 19 factors derived from sell-side analyst consensus data, covering forecast financial measures and analyst attention. For financial factors, it compares raw values with industry-relative rankings and quarter-over-quarter…
This Chinese equity screen combines a technical filter with size and liquidity conditions. It selects stocks with RSI below 65, circulating market value between 5 billion and 10 billion yuan, and prior-day trading value above 60 million yuan. The article…