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 presents a ProRealTime indicator that estimates price rate of change using weighted moving averages across the current timeframe and two higher timeframe proxies. Each rate line adds a scaled difference between a current weighted average and its…
This short description introduces an MQL5 library for calculating Optimal f, a position-sizing method based on Ralph Vince’s work on money management. The author explains that the library was pursued as an alternative to the Kelly Criterion, which they…
This document is a historical price table for a broad set of country and regional exchange-traded funds. It lists dates alongside one price series for each ETF, with examples spanning markets such as Japan, Brazil, Germany, India, and the United Kingdom. The…
The document summarizes research that builds a German FEARS sentiment index from Google search activity and links it to individual investors’ trades and stock returns. The index is constructed from searches for German terms related to expectations and…
The document presents a framework for trading a mean-reverting portfolio, often formed by holding one asset and shorting another. It models portfolio value with an Ornstein–Uhlenbeck process, estimates the long-run mean, reversion speed, and volatility by…
The document defines a price-based oscillator labeled Kurtosis and presents it as a market sentiment indicator that reflects price direction. Its calculation first takes a short exponential moving average of closing prices, computes the change between…
This forum exchange clarifies how VeighNa’s CTA strategy state file is used during initialization. A strategy first derives variable values from historical data and indicators, then reads saved JSON data to overwrite corresponding strategy variables.…
The document introduces hidden Markov models (HMMs) as a way to infer unobserved market regimes from observed asset returns. It explains the Markov assumption that the next state depends on the current state, and describes how regimes can change return…
The document explains the inputs and output buffers of a channel indicator. Its channel length setting determines how many bars are used to create the channel. A second setting controls the local peak and valley evaluation: the method considers a centered…
This stock screen looks for Shenzhen Main Board companies with annual return on equity above 15% in each of five years, a price-to-earnings ratio from zero to 29.01, and a price-to-book ratio from zero to 3.11. It also requires the daily high-low range to be…
This proposed stock screen selects main board shares with turnover between 3% and 12% and circulating market value between 5 billion and 10 billion yuan. It also requires large-order net volume to exceed 0.05 for at least three consecutive days. The article…
This forum post describes a feature calculated from the 000300.HIX index data. It derives daily returns from the close, calculates a rolling standard deviation over 250 observations, and divides that volatility measure by average turnover over the same…
This study outlines an experiment applying a Transformer model to short-horizon stock selection in China’s A-share market. Its target is each stock’s return over the next five trading days, using daily market data from 2015 through 2021. The inputs begin…
This Chinese-language excerpt summarizes a report about automatically generating trading strategies from time-series data. It frames conventional factor research, factor combinations, and rule combinations as labor-intensive manual work, then proposes using…
This document summarizes a research paper on factor timing, connecting it to market timing and factor investing. Its theoretical starting point is that an optimal portfolio corresponds to the stochastic discount factor (SDF). Under a conditional factor model…
The report summary explains a method for finding monthly indicators that may signal earnings changes in cyclical industries before standard financial statements are published. It covers real estate, autos, transport, coal, nonferrous metals, steel, building…
The article argues that traders can be misled by intuitive, familiar interpretations of price action and market narratives. Examples include buying a presumed leader after a technical pullback, expecting small caps to rise when large caps lead, or chasing a…
This indicator identifies thirteen common candlestick formations and marks them on a chart with labels and, for many patterns, directional arrows. The listed formations include doji, morning and evening stars, shooting star, hammer variants, harami,…
R-Squared is described as a linear regression indicator that can help assess how statistically strong the current trend may be. Although its display resembles an oscillator, the document frames its purpose as indicating the reliability of a trend rather than…
The document compares six programming-language options for building quantitative trading strategies: visual programming, EasyLanguage, Python, MATLAB/R, C++, and Java/C#. It evaluates them by capability, speed, extensibility, and learning difficulty, then…
This brief describes a custom linear regression channel indicator. It plots or calculates the regression line together with support and resistance line values, making those values available through indicator buffers for use by a trading platform or other…
This post documents an attempted BigQuant workflow for combining daily Chinese stock bars with prefactor and money-flow tables. The query joins records by date and instrument, selects price and valuation fields, calculates returns, and applies a non-null…
The module implements the two-step Engle–Granger approach to constructing a portfolio intended to be mean reverting. It uses ordinary least squares to regress a chosen dependent asset’s price on the other price series, defaulting to the first input column as…
This research summary treats intraday stock prices as time series rather than isolated observations. It applies empirical mode decomposition (EMD) to separate trend-like price signals from noise, then uses their relative strength to form a signal-to-noise…