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
The post describes a short horizon stock screen combining daily range, a “morning star” pattern, and a bounded opening price change. Its stated thresholds are amplitude above 1%, with opening change between −5% and 2.6%; the accompanying formula also limits…
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 Chinese-language post outlines an equity screening rule that ranks stocks by volume ratio and selects the top 100. It also proposes comparing rolling 7-day and 30-day moving averages, describing the filter as requiring the shorter average to be above…
This note presents a Chinese stock screen using two short-term conditions: a daily increase in the share of positions held above 5% and an opening-auction return between -2% and 5%. It also limits the stated sample period to 2021. The document interprets the…
This submission outlines an intraday stock-selection idea for a day when a market theme is breaking out. It proposes identifying a popular sector early, using large orders that hold at the daily price limit as a sign of a clear direction, then ranking…
This note describes a stock screen combining metaverse sector membership, a rounded price pattern, and a share price below 12 yuan. It suggests these filters as a way to identify lower-priced stocks in an emerging industry, and mentions RSI, MACD, and moving…
This Chinese community post outlines an equity screen combining three filters: membership in the metaverse theme, positive net buying attributed to major participants during the opening auction, and an appearance on the prior day’s public trading activity…
This Chinese post compiles a selection of 65 titles from a much larger collection of publicly released Springer books, focusing on data and machine learning. The bibliography spans foundations such as algebra, probability, statistics, optimization, and time…
This Chinese community post describes a daily stock screen requiring an amplitude reading above 1, a daily percentage change between -5% and -4%, and no limit-up session on the previous day. It presents the conditions as a way to identify volatile stocks…
This note outlines a stock screen for beverage and alcohol related companies. It combines turnover between 3% and 12% with an industry classification and measures of buying by large or extra-large orders during the opening auction. The stated rule uses an…
This note describes a Chinese equity screen combining turnover, order book depth, and institutional trading. It selects stocks with turnover between 3% and 12%, displayed best bid volume above best ask volume, and a positive institutional trading measure. A…
This notebook demonstrates a Monte Carlo approach to forecasting stock prices with geometric Brownian motion. It estimates drift and volatility from historical log returns, generates many simulated price paths, and splits the price series sequentially into…
This post outlines a Chinese equity screen using three activity and size filters: daily turnover between 3% and 12%, circulating market value between 5 billion and 10 billion yuan, and prior-day opening-auction turnover above 0.26. It gives a technical…
This Chinese-language post describes an equity screen for metaverse-related stocks. It combines an upward-sloping 30-day moving average with a measure intended to compare aggressive buying volume (外盘) against selling volume (内盘), using a stated threshold of…
This Chinese-language post describes an equity screen using three conditions: RSI below 65, turnover between 3% and 12%, and at least two limit-up price moves during the prior 500 days. It presents the screen as a way to find stocks with recent strong moves…
This stock-selection idea combines daily amplitude above 1, positive large-order net volume for at least three consecutive days, and a nonempty outstanding convertible-bond name. The post treats the bond condition as a way to identify companies that have…
This short-term stock screen selects shares with daily amplitude above 1, evidence of prior-day large-player control, and a closing price between the 20-period Bollinger middle and upper bands. The post explains that Bollinger Bands use a moving average and…
This stock screen combines a metaverse theme filter with RSI below 65 and a 15-minute MACD condition intended to identify a shrinking negative histogram. The post describes it as a way to find short-term trading opportunities in volatile stocks. Its formula…
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 example describes a short-term screen for Chinese stocks assigned to the metaverse theme. It filters for a volume ratio above 1.5 and below 6, a three-day limit-up sequence as of the prior day, and, in its final stated logic, market value below 500…
This stock-screening example combines a turnover filter, a reversal-style candle condition, and simultaneous moving-average crossover signals. Its stated selection logic requires turnover between 3% and 12%, a reversal pattern, and upward crossings among the…
This post outlines an A-share screen for stocks with amplitude above 1, excluding ST-designated shares, selected before 10 a.m., priced below 12, and matching a named five-step limit-up approach. The sample Python implementation operationalizes the last…
This post describes an A-share screen combining an intraday amplitude above 1%, a positive ten-day return below 35%, and an auction gain between -2% and 5%. It frames the amplitude as a measure of movement, the return band as a way to avoid both declining…