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
The document describes a moving median indicator for price data and explains the underlying Torben search algorithm. For each window, the routine finds its minimum and maximum, tests a midpoint, and counts values below, above, or equal to that candidate. It…
This document explains a moving median indicator based on Torben Mogensen’s selection method. A median is the central value in an ordered set and is less affected by outliers than common averages. The described method searches between the minimum and maximum…
This code implements a collection of cross-sectional and time-series equity alpha factors, mainly using close, open, high, low, volume, returns, and VWAP data. The factors combine operations such as rolling ranks, correlations, moving averages, extrema, and…
A trader asks where an individual can access tick-by-tick trades that include buyer or seller initiation, intending to calculate aggressive buying and selling volume at each price for an order-imbalance strategy. The reply says that ready-made aggressor-side…
This document describes a trend indicator that combines a Hull Moving Average (HMA), a modified HMA variant, and an optional Kalman-style filter. The filter updates a smoothed price estimate and velocity from the input series; the indicator then calculates…
This Chinese-language post outlines an A-share stock screen focused on companies classified in the metaverse industry. Its stated selection logic combines total assets above 200 million with an opening price near the 10-day moving average. The post also…
This document describes a chart overlay intended to make price history easier to inspect. Vertical lines mark hourly boundaries, with distinct colors for the starts of weeks, days, and months. Horizontal lines mark psychological round-number price levels and…
This stock screen selects Chinese A shares using a turnover range of 3% to 12%, excludes Beijing-listed shares, requires current volume above 10,000 lots, and includes an opening-price shape condition. The article describes the target as relatively active…
The document describes a script intended to compare MetaTrader 4 and MetaTrader 5 performance on a computer or hosted server. It combines procedural and object-oriented tests covering calculations, arrays, sorting, strings, graphical objects, canvas…
The document introduces two approaches to factor exposure in multi-factor models: using factor values directly, or estimating exposures through time-series regression. It distinguishes regression-based models, which aim to explain returns, from ranking…
The example shows how to use Pyfolio to create a returns tear sheet for a single stock. It retrieves daily returns for Facebook through a Pyfolio utility, then passes that return series to a tear-sheet function with a live-start date. The stated output is a…
This essay applies ideas from philosophy of science to judging trading strategies. It contrasts testable claims, which make predictions that evidence could disprove, with claims that cannot be meaningfully tested. For strategies whose edge is inferred from…
This short description introduces a modified Commodity Channel Index indicator designed to reduce noise. It adds a sensitivity threshold parameter, so users can adjust how responsive the indicator is, and it uses distinct colors to mark breaks above or below…
This Chinese-language post presents a stock-selection screen combining turnover, listing date, circulating market capitalization, and recent price movement. It targets stocks listed in the current year with market capitalization between 500 million and 1…
The document outlines a stock-selection screen using turnover between 3% and 12%, an outside-volume to inside-volume ratio above 1.3, and a minimum listing age represented by an unspecified number of years. It frames the filters as a way to combine trading…
The document gives a brief historical overview of quantitative investing. It describes how advances in computing made it practical to store and process large amounts of historical data, supporting the use of statistical and mathematical models in investment…
This document describes an indicator that estimates skewness and excess kurtosis over a selected rolling period of closing prices. Skewness summarizes distributional asymmetry, while kurtosis describes tail weight relative to a normal distribution. The…
The Detrended Synthetic Price oscillator is described as a way to display price movement after removing a trend component. Its calculation uses the difference between an exponential moving average and a half-period moving average. The result is intended to…
This indicator estimates an asset’s volatility from the high and low of smoothed Heiken Ashi candles. It takes the candle range, converts it to points, then rounds that value to a grid defined by a starting level and a level increment. The resulting levels…
The document describes an indicator that applies K-means clustering to historical price points. It groups prices by density and treats each cluster’s center, or centroid, as a potential area of concentrated liquidity. The intended use is to plot support and…
This educational article introduces support vector machines (SVMs) as classification models, with examples framed around separating two classes using features. It explains the maximum-margin objective: choose a decision boundary that stays as far as possible…
This report challenges mean-variance optimization assumptions that returns are normally distributed, volatility captures risk symmetrically, and portfolios should maximize return per unit of risk. It instead frames investor concerns as preserving principal…
Historical volatility describes how widely an instrument’s returns vary over a selected period. The document presents standard deviation as a common way to measure this dispersion and explains that higher readings indicate larger price fluctuations and…
This post proposes screening stocks for a daily high-low range above 1% during 2021 and year-over-year growth in net profit attributable to parent-company shareholders above 20% and no greater than 100%. It interprets the range threshold as a sign of price…