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-screening proposal targets companies in the metaverse industry that have had more than two limit-up sessions in the recent ten-day window and have just formed a KDJ golden cross. It calls for screening before 10:00 on each trading day and…
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 short platform discussion explains that an adjust factor is used to convert a stock’s real price into an adjusted price. Adjusted prices, including forward- and backward-adjusted series, are intended to keep price charts continuous across corporate…
This Chinese stock-screening post describes a rule based on price range, recent turnover, and limit-up frequency. Its initial description calls for an amplitude above 1, prior-day actual turnover between 3% and 28%, and more than two limit-up sessions in a…
This stock-screening rule selects shares with turnover between 3% and 12%, a seven-day falling-price pattern, and no limit-up session on the previous day. The document gives both a platform-style condition and a Python example, and explains the intended…
The document introduces Temporal Routing Adaptor (TRA), a model designed to learn multiple trading patterns from stock market data. It describes using TRA with Qlib datasets and workflows, and notes that the paper’s reproduction setup first trains a backbone…
This Chinese equity screen combines price amplitude above one, appearance on the previous day’s market top list, and a positive price-to-earnings ratio. The article interprets amplitude as a sign of short-term volatility, top-list inclusion as a possible…
This Chinese equity screen looks for stocks with price amplitude above one, an opening price near the ten-day moving average, and simultaneous bullish crossover signals from three indicators. The examples use MACD, RSI, and KDJ: MACD and KDJ cross above…
This stock screen combines three conditions: net buying today must exceed five percent, the previous day’s turnover must be above 60 million, and the ten-day price gain must be positive but below 35 percent. The document presents these as signs of buying…
The document proposes a Chinese equity screening approach that selects robot concept stocks with daily amplitude above 1%, float capitalization below 10 billion, and no ST designation. It specifies screening before 10 a.m. and says a five-step limit-up…
This Chinese-language article describes an equity screen restricted to the metaverse concept group. It selects stocks whose close is above the five-day moving average and whose weekly MACD is above zero, using these conditions as short- and medium-term trend…
This post describes a Chinese equity screen combining three conditions: a positive MACD reading, membership in selected beverage and alcohol import-export industry classifications, and a daily percentage change below a stated ceiling. Its example…
This Chinese stock-selection rule screens for companies associated with the metaverse theme, with the previous day’s actual turnover rate between 3% and 28%, while excluding stocks on the STAR Market. The stated rationale is that turnover may reflect…
This sample describes a high-dividend stock-selection model for Chinese equities. The process excludes special-treatment stocks, suspended securities, and Beijing Stock Exchange listings. It then screens for larger companies by market-capitalization rank,…
This sample strategy selects Chinese equities using a dividend yield ranking alongside size and valuation filters. It first removes special-treatment stocks, suspended shares, and Beijing Stock Exchange listings. From the remaining universe, it favors…
This brief description introduces a semaphore-style signal indicator built from crossovers between lines of the Digital CCI Woodies indicator. It identifies the indicator’s author and notes that its implementation relies on a SmoothAlgorithms library for…
This forum post reports a suspected data-quality problem in a Chinese stock valuation dataset. The author observed that the September 14, 2022 snapshot appeared to contain more than 1,600 missing or erroneous records, while the adjacent dates seemed to have…
This article describes a Chinese stock screening rule that combines daily price range, a recent reversal-style candlestick condition, and a low KDJ value. Its stated final criteria are amplitude above 1%, a reversal pattern within the past three days, and K…
This A-share stock screen selects shares with a daily trading range above a stated threshold, positive estimated main-fund flow on the prior day, and MACD above its zero line. The MACD condition is intended to identify stocks with positive trend momentum,…
This A-share screening idea combines an RSI below 65 with an external-to-internal trading volume ratio above 1.3 and a reversal or engulfing pattern. The article also describes filtering for a positive but bounded ten-day price change and checking recent…
This stock screen combines daily amplitude above 1, a positive weekly MACD reading, and a share price in the 18-to-19 yuan range. The post frames amplitude as a measure of movement, the weekly MACD condition as a sign of upward momentum, and the price band…
This Chinese stock-selection example combines a 14-period RSI below 65 with a history of at least two limit-up sessions over the prior 500 days, then ranks qualifying names by a measure of trading heat. The stated rationale is to pair a short-term technical…
The Alan Square, also called DaBox, is a price action framework built from the prior period’s high and low. It marks the range boundaries, midpoint, quarter levels, and extensions, then projects diagonal lines from key levels. Major angles are described as…
This brief indicator description identifies a tool that draws support and resistance levels using daily charts. It names the original author and notes that an earlier implementation was published in 2008. Beyond its stated purpose and daily-chart basis, the…