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 idea combines three conditions: MACD is above zero on the current day, a prior-day condition described as main-force control is met, and MACD was below zero two days earlier. The proposed interpretation is that the positive current…
This note describes a technical screen for stocks in the metaverse theme. It looks for simultaneous bullish crossovers in MACD, KDJ, and DMI, together with a minimum daily high-low range relative to the prior close. The final stated threshold is above 0.8,…
This short-term A-share screen looks for stocks with an intraday range above 1%, relative volume between 1.5 and 6 times its five-day average, current volume above 10,000 lots, and an open at the session low. The article interprets these filters as seeking…
The screen selects Chinese beverage and alcohol related stocks with turnover between 3% and 12% and a prior closing price above its 250-day moving average. The article presents turnover as a measure of trading activity and the long moving average as a way to…
This stock-selection screen combines three conditions: at least five moving averages converge, the tradable share count is no more than 5.5 billion shares, and the stock has hit its daily upper price limit more than twice within ten days. The stated…
This Chinese-language article presents a stock screen combining four conditions: daily high-to-low range above one percent, membership in a robotics-related concept, circulating market capitalization below 10 billion yuan, and a nonempty name for an…
This post proposes screening stocks for price amplitude above 1, upward-diverging moving averages, and previous-day turnover above 8%. It frames amplitude and moving-average behavior as measures of recent price action and turnover as a gauge of market…
This Chinese-language post describes an equity screening rule that selects stocks with a 14-period RSI below 65, three consecutive bearish sessions, and a weekly red-bar signal. The combination is presented as a way to find stocks that have recently weakened…
This Chinese stock-selection example screens for securities whose codes begin with 60, whose turnover rate is between 3% and 12%, and whose daily percentage change falls between a 4% and 5% loss. The accompanying sample workflow obtains a listed-stock…
This Chinese stock-screening example combines three technical conditions: a 14-period RSI below 65, the 20-day moving average above the 120-day moving average, and a condition labeled “main uptrend start.” The latter is defined as the 30-day highest high and…
This stock-selection rule combines three conditions: membership in the metaverse theme, a daily high-low range above 1%, and a KDJ reading below 20. The article describes the range condition as seeking more active price movement and treats the low KDJ value…
This stock screen ranks shares by capital-flow strength, from strongest to weakest, and filters for a positive price-to-earnings ratio and a dividend payout ratio above 25% in 2019. The stated rationale is to combine evidence of investor inflows with…
The proposed screen selects main-board stocks using three conditions: daily amplitude above one, large-order net volume above 0.05 for at least three consecutive days, and outside volume more than 1.3 times inside volume. The document interprets amplitude…
The proposed equity screen combines daily amplitude above 1, a turnover activity measure between 0.5 and 2, and weekly MACD above its signal line and zero. The activity measure is described as yesterday’s turnover multiplied by today’s auction volume…
This stock selection rule combines three daily price conditions: percentage amplitude above 1, a current high equal to the highest high across the current and previous day, and a rising 30-day simple moving average. The intended screen seeks shares with…
The proposed stock screen combines three conditions: price amplitude above a stated threshold, a shortening negative MACD histogram on a 15-minute interval, and association with the metaverse theme. The idea mixes a volatility filter, a short-horizon…
The document presents TS-Boost as a machine-learning framework for equity factor selection, motivated by two challenges in financial data: changing distributions across time and low signal-to-noise ratios. Instead of pooling observations from many dates into…
The discussion explains why a backtest’s cumulative return can appear inconsistent with profit and loss shown in exported position details. The key distinction is that the export described here records stocks still held at the end of each day. It therefore…
This note describes a short-term A-share screen using daily amplitude above 1% and relative volume between 1.5 and 6, measured against a five-day average. The article's stated logic adds an exact closing-price condition of 18.5, and it characterizes the…
This note presents a technical stock screen requiring daily amplitude above 1%, a current low below the previous day's low, and a rising 30-day moving average. It frames the wide range as a sign of heightened price movement, the lower low as a pullback…
This research note explains how one-dimensional convolutional neural networks can extract local patterns from financial time series, and how ResNet skip connections help address performance degradation as networks deepen. Its proposed stock-ranking setup…
This note describes an A-share stock screen combining daily price amplitude above 1%, a reversal pattern, and positive trailing-twelve-month P/E. The amplitude condition targets stocks with larger daily ranges, while the reversal condition is intended to…
This document describes a proposed screen for stocks in the Chinese metaverse theme. It combines a price condition—average price above the five-day moving average—with a MACD condition referring to a value below zero two days earlier. The article frames the…
This document outlines an A-share stock screen based on turnover between 3% and 12%, excluding Beijing-listed shares, then ranking candidates by a measure of individual-stock popularity or market heat. It presents the turnover range as a way to focus on…