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.
22,592 documents
This stock selection rule combines three filters: daily price amplitude above 1, a listing history longer than one year, and at least one limit-up event in the prior 25 days. The accompanying explanation treats recent limit-ups as a possible sign of market…
The document describes an intraday strategy that combines classification and regression models built with XGBoost to rank stocks by predicted daily price change. Its features include overnight returns and opening-auction behavior, such as staged price moves,…
This brief forum post asks how to express a condition in Python for a security’s low price to cross below its 60-day moving average. The visible example begins to describe a method that compares the prior period’s low and moving average with their current…
This article collects practical lessons from building supervised machine learning strategies for stock selection. It recommends keeping training and test data separate and splitting financial time series chronologically, since random splits can mix market…
This Chinese equity screening proposal combines three conditions: a price amplitude above 1%, free float no greater than 5.5 billion shares, and short-, medium-, and longer-term moving averages aligned upward. The article interprets the amplitude filter as…
This overview proposes using machine learning to support value investing by combining financial statements, market data, and macroeconomic information. It lists a broad set of candidate measures, spanning performance and risk statistics, valuation and…
This document describes a Chinese equity screen combining turnover between 3% and 12%, seven consecutive down days, and a morning price condition below 6%. It presents the setup as a way to find stocks in a pullback while accounting for trading activity and…
This Chinese-language article proposes screening mainland Chinese stocks in the metaverse sector using two price conditions: the 9:25 price change must be below 6%, and the stock must have more than two limit-up days within the prior ten days. The first…
This report examines whether updating fundamental signals more frequently can improve stock selection during China’s annual report season. It argues that factor signals decay over time, but more frequent rebalancing offers limited benefit for fundamental…
The proposed screen uses Chinese A-share data from 2021 onward, compares the 20-day and 120-day moving averages, and keeps stocks where the shorter average is above the longer one. It then ranks candidates by capital strength and selects the top 100. The…
The screen selects Chinese A-share stocks using three conditions: buying-position share above five percent on the current day, no limit-up session on the prior day, and more than two limit-up sessions during the past ten days. The accompanying explanation…
This document outlines a Chinese stock screen for companies associated with the metaverse concept. It selects shares with circulating capital no greater than 5.5 billion shares and at least one limit-up event during the preceding 25 days. The rationale is…
This document describes a Chinese A-share screening rule combining three conditions: RSI below 65, the ratio of external to internal trading volume above 1.3, and the closing price above its five-day moving average. The indicators are presented as a way to…
The document describes a stock-selection screen combining MACD above zero, upward alignment among current moving averages, and a weekly five-period average crossing above a ten-period average. It interprets these conditions as evidence of positive momentum…
The document introduces moving averages as a way to smooth price data and describe trends. It distinguishes shorter and longer averaging periods, gives the arithmetic average as the basic calculation, and also describes a weighted recursive SMA convention…
This note proposes a Chinese stock selection screen requiring MACD’s DIF line to be above zero, a short moving average to be rising, and positive institutional net buying. It interprets these conditions as evidence of an upward trend and institutional…
This note describes a short-term Chinese stock screen combining prior-session amplitude above 1%, a free float no larger than 5.5 billion shares, and an opening increase below 6% at 9:25. It presents the conditions as a way to find volatile, relatively…
The article describes a Chinese equity screening rule that selects stocks with turnover between 3% and 12%, three consecutive declining sessions, and concentration below 20%. It presents the decline pattern as a technical condition and describes the…
This Chinese-language article outlines a stock screen combining a 14-period RSI below 65, three consecutive bearish candles, and return on equity above 15% across five years. The stated aim is to find stocks with recent technical weakness alongside a record…
This article proposes a short-term Chinese equity screen using three conditions: a daily range greater than one, a prior-day 9:15 indicative matching price at the limit-down level, and a 10-day return above zero but below 35%. It adds an exclusion for stocks…
This article describes a Chinese equity screening rule that combines a daily high–low range of at least one unit, return on equity above 15% in each of five years, and market capitalization of at least 200 million. It presents the criteria as a way to…
The note describes Larry Williams' Pro-Go oscillator as an indicator for daily charts. It focuses on a comparison between a Professional line and a Public line, interpreting their divergence as a possible discrepancy between professional activity intended to…
This Chinese-language research report outlines an equity index evaluation framework based on Barra-style risk factors. It proposes decomposing index returns into market, industry, and style contributions, including size, valuation, and volatility, then using…
This short-term Chinese equity screen looks for stocks with an intraday range above 1%, current volume above 10,000 lots, a higher open, and a positive return for the day. The stated rationale is that range and volume indicate active trading, while a gap up…