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.
21,023 documents
This research summary examines the low idiosyncratic volatility effect in China’s A-share market. It estimates volatility from the annualized standard deviation of residuals in CAPM, Fama–French three-factor, and Carhart four-factor regressions fitted to the…
This platform support note explains the intended use of a high-frequency feature extraction module. It takes fields from a specified Level-2, one-minute Chinese stock bar table and applies expressions compatible with pandas and NumPy to calculate…
The discussion explains how to repeatedly reduce a model’s factor list using feature importance. The example starts with 15 factors, removes the three with the lowest importance after a training and backtest run, and repeats the process until five factors…
This brief note describes an extension to a limit-channel indicator that displays calculated states as a colored histogram. It groups channel levels into three speeds: inner levels are fastest, middle levels are intermediate, and outer levels are slowest.…
The document explains a Brinson framework for separating portfolio returns into a policy benchmark, active asset allocation or timing, security selection, and their interaction. The benchmark reflects long-term asset-class weights and passive returns.…
This document describes a chart indicator for tracking groups of long and short symbols together. Users can configure up to 50 symbols in each basket, switch the chart to a listed symbol, move the display, and select the week for its historical statistics.…
This study asks whether corporate bonds become more vulnerable to price swings when held mainly by open-end funds with illiquid portfolios. It builds a bond-level fragility measure in two stages: first estimating each fund’s portfolio illiquidity from its…
This document introduces factor research as a quantitative way to study characteristics that may help explain asset returns and risk. It names market capitalization, quality, momentum, low volatility, and yield as examples, and describes using statistical or…
This post proposes screening Chinese stocks for a daily price move of at least one percent, a nonempty name for an outstanding convertible bond, and exclusion from a specified market segment. It presents the range condition as a way to identify active stocks…
The document introduces the Bias indicator, which expresses a closing price’s percentage deviation from its moving average over a chosen number of days. The calculation compares the close with the moving average, subtracts the average, and scales the…
Return on equity (ROE) measures net income relative to shareholders’ equity, expressing how much profit a company generates from its equity base. The document gives the formula and a simple numerical illustration, then describes how investors may interpret…
This indicator compares each candle with the immediately preceding candle, looking for opposing changes in candle size and volume. It labels a candle as a growing divergence when its range increases while volume falls, and as a falling divergence when its…
POGO is described as an oscillator intended to display the mean bar size over a selected period. Its calculation begins with the difference between each bar’s open and close, then applies a moving average to those values. The user can adjust the calculation…
The post describes a simple Chinese A-share stock screen requiring daily high-low movement above 1%, a nonempty outstanding-convertible-bond name, and a share price around 18.5 yuan. Its final restatement widens the price condition to 18–19 yuan, while the…
The document outlines an exploratory method for studying whether historical indicator patterns relate to later price movement. It encodes a sequence of MACD values over a lookback window, uses that sequence to name a CSV file, and records how often the…
The discussion compares quantitative research practices in China and overseas. It says Chinese investors more often try to predict stock prices directly, while overseas researchers may estimate missing observations, factor values, company revenue, or…
This brief description outlines an MT5 indicator that constructs a moving line by extrapolating a fourth-degree polynomial. It describes deriving candidate lines from a sine-like curve and from an axial or nearly constant line, with different line-power…
This introductory guide lays out five areas for developing quantitative trading capability: mathematics and statistics, programming, financial knowledge, strategy research, and practical testing. It highlights time-series and cross-sectional econometrics,…
The document describes an indicator that groups broker tick quotes by server hour over a configurable history window. It reports median and 90th-percentile spreads, with optional mean and maximum statistics, and can compare the spread with a user-entered…
This indicator combines a CCI-like calculation on changes in closing price with two stages of exponential smoothing. It then computes the standard deviation of the smoothed oscillator and uses rolling highs and lows of that deviation to create dynamic upper…
This stock-screening concept combines price amplitude above one percent, RSI below 65, and a shortening negative MACD histogram on a 15-minute chart. The text interprets shrinking negative bars as potentially weakening selling pressure and a possible rebound…
Gold Dust proposes a robustness check for optimized trading systems that addresses the instability of financial-market statistics. Instead of optimizing one parameter set on one historical interval and forward-testing it, the method optimizes separate…
SatlMacd is described as an oscillator built from the averaged difference between the SATL digital filter and the closing price. The description identifies the two components and the averaging step, but does not explain the filter's construction, the…
This guide outlines a workflow that combines TQ EDB market and indicator data services with Coze as a conversational research assistant. After adding the EDB skill, a researcher can describe a task and request data retrieval, idea checks, simple backtests,…