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.
4,510 documents
This stock-selection proposal combines three filters: membership in the metaverse theme, positive net buying attributed to major participants during the opening auction, and a close above the middle Bollinger Band but below its upper band. The article…
The article presents five principles for short-term stock trading: prominent stocks may attract liquidity despite looking expensive; near-term prices reflect the balance of buying and selling shaped by expectations and sentiment; traders should seek gaps…
This research outline proposes allocating among equity industries by tracking the behavior of different market participants. It motivates industry rotation with the observation that returns can diverge substantially across sectors and styles, so broad asset…
The document describes a commodity futures strategy that ranks 28 markets by changes in Twitter-derived sentiment. It calculates daily sentiment from keyword-matched posts using a financial sentiment dictionary, then forms equal-weighted long and short…
This post describes a Chinese stock selection screen based on turnover between 3% and 12%, appearance on the previous day’s trading leaderboard, and a current control indicator above 21. It also gives a formula-style expression and a Python example that…
This market snapshot reviews several crypto themes: a sharp contraction in AI-agent token capitalization alongside rebounds in a few assets, relative strength in DeFAI, and a newly announced WLFI fund focused on major crypto assets. It also discusses…
This post describes a Chinese equity screen combining recent large-order net buying, a high current-day position increase, and a historical dividend ratio threshold. It presents the flow conditions as signs of investor interest and the dividend filter as a…
This Chinese A-share screening proposal filters for stocks with an intraday range above 1% during 2021, then keeps observations where price change multiplied by an estimate of very large order flow is positive. The intended interpretation is that volatility…
The document summarizes CapTE, a model for predicting stock movements from social media text. A Transformer encoder extracts semantic features from posts, while a capsule network is used to represent structural relationships in the text. The approach is…
This stock-selection idea screens Chinese equities associated with the metaverse theme, requires a positive institutional-flow reading, and selects stocks whose closing prices lie between the middle and upper Bollinger bands. The proposed rationale is to…
These notes summarize ideas from a Chinese trading book through ten named principles and effects. They cover how payment frequency shapes perceived gains and losses, how unknown factors and nonlinear systems complicate market decisions, and how penalty kicks…
The article proposes screening Chinese A shares in the metaverse industry for stocks reported on the prior day’s Dragon-Tiger list and with first-level bid volume greater than first-level ask volume. It interprets the quote imbalance as a sign of positive…
This note proposes selecting stocks in the metaverse theme whose previous closing price is above the 250-day moving average, then applying a filter for company characteristics. It describes the theme as a way to target a popular sector and the long moving…
This proposed Chinese equities screen selects non-special-treatment stocks with daily amplitude above 1 and a product between 0.5 and 2: the previous day's turnover rate multiplied by today's opening-auction volume divided by the previous day's volume. It…
This document summarizes a research approach that uses Google Trends search activity to inform equity portfolio weights. It treats search volume as a measure of how popular a stock is and assumes that popularity is related to risk. The portfolio therefore…
This Chinese stock-screening article combines three conditions: a 14-period RSI below 65, best-bid volume greater than best-ask volume, and an opening price within five percent of the ten-day moving average. The approach uses RSI as a price-condition filter,…
This Chinese A-share screening concept selects stocks whose daily high-low range exceeds a stated threshold, excludes stocks that reached the daily price limit the previous day, and ranks the remaining names by individual-stock market heat. The rationale is…
The document summarizes a 2020 study on whether investor attention measured through Baidu search activity can help forecast volatility in Chinese equities. The researchers compare a baseline GARCH model with an expanded version that includes search volumes…
The document describes a Chinese stock screen using ranked fund-flow strength, a 2019 dividend ratio above 25%, and a 15-minute MACD histogram whose negative bars are shortening. The MACD condition is presented as a possible sign of improving short-term…
This stock-selection approach combines a daily turnover band of 3% to 12%, a positive product of price change and large-order net flow, and a Morning Star candlestick signal associated with Kute Intelligent. The document describes the pattern as a way to…
The document outlines a proposed screen for stocks associated with the metaverse theme. Its final stated rule selects companies with market value no higher than 10 billion yuan, circulating shares no greater than 5.5 billion, and a daily increase in holdings…
This note describes a stock-selection screen for Chinese equities that keeps stocks with turnover between 3% and 12%, excludes Beijing-listed shares, and ranks candidates by a money-flow strength measure. Its formula reference relates the strength measure to…
This weekly crypto market report assesses a recovery in prices by combining spot performance with trading volume, volatility, open interest, funding, order book depth, ETF flows, stablecoin issuance, and DeFi credit measures. It interprets rising prices…
This document describes a market sentiment indicator that classifies conditions as bullish or bearish using limit order book data on centralized markets. Its inputs include minimum qualifying order volume, minimum order count, and thresholds for differences…