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 summary describes a market-timing approach that uses a convolutional neural network to extract patterns from lower-dimensional index features, including technical indicators, and classify expected returns. Predicted return classes are then used to drive…
This report summary examines whether northbound capital flows into mainland Chinese equities can inform market timing and portfolio selection. It describes threshold signals for daily and weekly flows, then a dynamically adjusted timing indicator. It also…
This article presents five ways to manage exits from stock positions: set an initial price threshold before entry; raise the stop to break-even after a favorable move; trail it as the price advances; exit when price breaks a trend line or moving average; and…
The document addresses how to retrieve financial figures from multiple quarters and combine them into a factor for analysis. The examples ask about comparing current-quarter cash flow with the prior quarter to measure change, and averaging current and…
The document outlines a proposed system for automating A-share investment research reports. It describes combining company and industry information, financial analysis, valuation, price-chart analysis, and analysis of news and announcements. A LangGraph…
The document describes an A-share screening rule for companies assigned to the metaverse industry. It combines a float-size ceiling with an ownership-concentration ceiling, then returns qualifying stock codes and names. The accompanying Python example…
This stock-selection rule filters for a high–low range above 1% of the high, a closing price of exactly 18.5 yuan, and circulating market value of at least 10 billion yuan. The document includes example selection logic and sorts qualifying names by trading…
This stock screen combines a daily range condition with sustained profitability and a momentum indicator. It selects shares whose high–low range exceeds an ATR-based threshold, whose return on equity stayed above 15% across five years, and whose 14-period…
This QlibRL example describes how to configure and run a reinforcement learning workflow for executing orders in one asset. The training setup defines a simulator with 30-minute steps, a categorical action space, a full-history state representation, a…
This post proposes a Chinese equity screen combining three conditions: daily amplitude above a threshold, at least two limit-up events within a 500-trading-day window, and a reversal or engulfing-style candle condition. It gives formula references and an…
The proposed screen selects main-board stocks with circulating market value between 5 billion and 10 billion yuan, turnover between 3% and 12%, and a stated daily maximum decline between 4% and 5%. The article presents the filters as a way to find stocks…
This stock-selection post describes a screen using three short-term conditions: a positive ten-day return below 35%, daily amplitude above 1%, and a stated concentration measure below 20%. It frames these filters as a way to identify stocks with recent gains…
This community post proposes a Chinese stock screen within the metaverse industry. It filters for prior-session actual turnover between 3% and 28%, an opening-auction price move ranked among the strongest in the market, and combined net buying by very large…
This weekly Chinese equity research note reviews long-short screens built from high-frequency and technical factors. The listed signals include return skewness, downside volatility share, opening-period buying interest and large-order flows, reversal,…
This article reviews global equity factor performance in the third quarter of 2021 and compares defensive factor positioning. It reports that momentum and low residual volatility led the pure factor results, while liquidity lagged. Regional index outcomes…
This article reviews global equity factor performance in the third quarter of 2021 and compares defensive factor positioning. It reports that momentum and low residual volatility led the pure factor results, while liquidity lagged. Regional index outcomes…
This Chinese-language article describes an equity screen for Shenzhen main-board stocks associated with the metaverse theme. It selects stocks with a positive return, positive price-to-earnings and price-to-book ratios, and upper bounds on both valuation…
This document outlines a stock-selection screen that ranks securities by capital strength and requires weekly MACD to be above zero, alongside a year-based filter referring to 2021. It explains capital strength through trading volume and value, and describes…
This document presents a Chinese equity screen for Shenzhen Main Board stocks, combining turnover from 3% to 12%, circulating market capitalization from 5 billion to 10 billion, price-to-earnings ratio from 0 to 29.01, and price-to-book ratio from 0 to 3.11.…
This document proposes screening stocks whose codes begin with 60, keeping those with turnover between 3% and 12%, then ranking them by a measure described as capital strength. The commentary presents the ranking as a way to identify actively financed market…
This document describes a Chinese stock screen using amplitude above 1, a stated K-line value below 20, and prior-day actual turnover between 3% and 28%. It presents these conditions as a way to find stocks with notable price movement and moderate trading…
The post proposes screening Chinese equities for elevated daily range, at least one daily gain of 10% or more during the past 25 trading days, and a pre-open price change below 6%. It then extends the screen with company and industry comparisons, including…
This proposed Chinese stock screen looks for shares associated with both the metaverse and robotics, with a newly formed bullish KDJ crossover and a circulating market capitalization below 10 billion yuan. It adds a time and trading-status restriction:…
This Chinese A-share screening idea combines three technical conditions: at least five moving averages are described as converging, the KDJ indicator has just formed a bullish crossover, and the 20-day moving average is above the 120-day average. The post…