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 indicator compares a candle’s price movement with its tick volume and plots the result as a histogram with a smoothed moving-average signal line. The calculation can use either the absolute open-to-close difference or the high-to-low range, divided by…
This article outlines an A-share stock screen that combines daily trading activity and company fundamentals. It selects stocks with turnover between 3% and 12%, market capitalization below 10 billion yuan, and no losses, then ranks candidates using revenue…
This research note describes a daily equity alpha approach that uses supervised neural networks to generate many candidate factors from designed factor units. It then transforms the original inputs into weak, mutually orthogonal factors and weights them…
This document presents an Ornstein–Uhlenbeck (OU) process as a framework for distinguishing mean-reverting behavior from persistent drift. It contrasts the model with conventional volatility bands, arguing that bands around a moving average do not by…
MaxMinRange is described as a two-part indicator for displaying price extremes within candlesticks. One component tracks the maximum values associated with upward movement and is plotted above zero; the other tracks values associated with downward movement…
This guide outlines a crypto pairs mean-reversion strategy built around cointegration rather than correlation alone. It proposes testing logged price series with the Engle–Granger method, estimating a regression hedge ratio, and checking the resulting spread…
The document introduces momentum deviation as a variation on standard deviation. Rather than calculating dispersion from price itself, it applies the calculation to price momentum. It says the method is designed to use little CPU and that its values are…
Recursive analysis helps check whether indicator values depend materially on how many startup candles are available. Recursive formulas use prior values, so an indicator calculated over the full backtest history may differ from one calculated in a dry or…
Recursive indicators depend on preceding values, so their outputs can change when calculations begin with different amounts of historical data. A backtest may use a long requested date range, while a live or dry run may have fewer candles available from the…
The document introduces ALGLIB, a numerical analysis library ported for use with MetaTrader. Its listed capabilities include linear algebra, optimization, interpolation, Fourier transforms, differential equations, statistical tests, and data analysis methods…
This indicator description combines Lyapunov’s theory of movement stability with the Hodrick-Prescott filter, a time-series smoothing method used to distinguish longer-term trends from shorter-term variation. It exposes two inputs: the filter calculation…
This study adapts SinGAN, a multiscale generative adversarial network trained on one sample, to generate financial return sequences. Its pyramid trains progressively across scales: coarse layers represent broad, low-frequency structure, while finer layers…
Zero Point Force (ZPF) is a market-climate indicator that multiplies smoothed volume by the difference between fast and slow moving averages of closing price, scaled by one half. Users can configure the periods and calculation methods for both price averages…
The document describes an indicator that generates semaphore-style trading signals when the main and signal lines of an Adaptive Relative Vigor Index oscillator cross. It identifies the indicator’s original author and notes that it depends on a separate…
The indicator estimates recent volatility by counting local highs and lows over a rolling lookback. A peak is identified when surrounding bars have lower highs, while a trough has higher lows; the BarsBefore and BarsAfter settings determine how many…
This module describes ways to select groups of stocks for vine copula analysis, a component of a statistical arbitrage approach. It starts from price histories, calculates daily returns and ranked returns, and narrows candidate partners for each target stock…
This paper-reading digest summarizes several computer vision methods: InstanceFCN for generating object instance masks from position-sensitive score maps; a two-stream residual network that combines full-resolution detail with pooled features for…
The document introduces an oscillator based on the inverse Fisher transform, described as an extension of John Ehlers’s approach. It notes that this version lets users choose the price input and adjust the periods instead of relying on a fixed oscillator…
The document summarizes research using public Northbound investor holdings and trading-flow data to build 12 factors for Chinese equities. It reports testing those factors from December 2016 through December 2019 across Northbound-held stocks, the CSI 800,…
This overview distinguishes price-based market data from blockchain activity data and describes metrics that may help frame digital-asset valuation. Market capitalization is token supply multiplied by price, while trading volume is used as a rough gauge of…
This indicator estimates a separate average high-low range for each calendar month from the available monthly price history. For a January bar, for example, it uses the historical ranges of January bars to set the current band width. The range is centered on…
This stock-selection rule combines a turnover band of 3% to 12%, appearance on the prior day’s top-trader or unusual-trading list, and declines across the latest three sessions. The stated idea is to focus on moderately active shares that attracted market…
The document introduces an adaptive price filter through an intuitive explanation of Kalman filtering. It starts from the idea of a moving average and describes adjusting the filter’s responsiveness to balance two sources of uncertainty: how much price is…
This research summary argues that bond fund rankings based on a single historical performance measure can be distorted by differences in market style, objectives, holdings, manager skill, fund size, and risk controls. Its proposed approach narrows the…