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 adds a three-level trend-strength cue to BinaryWave. It calculates the standard deviation of the BinaryWave indicator and compares it with two user-set thresholds. When the value falls between the thresholds, a small dot appears on the moving…
This Chinese-language post proposes screening stocks for daily range above one percent, a closing price of 18.5 yuan, and an opening price within roughly two percent of the 10-day moving average. It describes the combination as a way to find moderately…
The article summarizes research on whether forced mutual fund selling affects the prices and liquidity of related stocks. It describes a learning mechanism: investors may initially interpret a peer stock’s decline as evidence of negative information about…
The indicator estimates the direction of a price or derived series by fitting a regression line to a selected set of observations and measuring its slope. Inputs can include closing, high, or low prices, as well as moving averages, and the tool is described…
This indicator estimates whether the next candlestick may move in the same direction as the current one. It calculates a candle measure from the difference between close and open divided by volume, scales that value, and compares it with its moving average…
This example tests whether market capitalization is associated with next-day stock returns using repeated cross-sectional ordinary least squares regressions. It joins Chinese stock factor data to daily bars, calculates forward returns from the next close,…
The document describes a stock screen combining daily amplitude above 1, RSI below 65, and large-order net flow above 0.05 for at least three consecutive days. It gives a formula for amplitude relative to the previous close and suggests using the buy-side…
The document defines a technical indicator that combines Bollinger Band width with average true range. Its stated calculation takes the distance between the upper and lower Bollinger Bands and subtracts average true range multiplied by a configurable…
This reference catalogues TA-Lib functions and their input fields for calculating common trading indicators. It groups examples into overlapping price studies, volatility and volume-price measures, cycle functions, price transformations, momentum indicators,…
The article summarizes research on whether active mutual fund managers adjust trading to anticipated stock-picking opportunities. It defines stock-selection timing as trading more when opportunities to hold positive-alpha stocks are greater and less when…
This brief indicator description introduces a market-state component based on correlation, drawing on a June 2020 TASC article about using correlation as a cycle indicator. The referenced approach presents three possible ways to determine market trend, and…
This overview surveys unsupervised learning through two groups of methods: dimensionality reduction and clustering. For dimensionality reduction, it describes PCA as a way to project high-dimensional features into fewer dimensions using covariance-matrix…
This note summarizes the AlexNet deep convolutional neural network described in the ImageNet classification paper. It outlines the model’s use of multiple convolutional channels, five convolutional stages and three fully connected layers, and explains how…
The document describes a revised script for emulating ticks during indicator testing, with support for managing multiple indicators. It says the example demonstrates how to include an indicator using a linear regression indicator, and that the inclusion…
This indicator identifies price-chart fractals at several dimensions and displays them at the same time. Its supported search range runs from 1-by-1 through 10-by-10, while minimum and maximum dimension inputs let users select which sizes to show. Upper and…
This numerical methods note explains an explicit finite-difference scheme for the one-dimensional heat equation. It approximates the time derivative with a forward difference and the spatial diffusion term with a centered second difference, then advances the…
This support thread explains that NaT represents a missing or invalid date value and describes a simulated trading failure in BigQuant. The reported traceback shows NaT reaching a date lookup in the data portal, followed by a comparison error between an…
The document describes APB, a family of cross-sectional stock factors intended to estimate buying and selling pressure from the relationship between price and trading volume. Its premise is that buying concentrated at lower prices and selling concentrated at…
This research summary reviews portfolio optimization choices, including transaction-cost penalties, turnover and tracking-error limits, risk aversion, position bounds, style-factor exposure, and limits on the number of holdings. It explains that stricter…
This study reviews Chinese equity-oriented mixed funds over 2010–2020 and compares their performance with several domestic equity benchmarks across value- and growth-led market periods. It reports that the fund group’s relative results varied with market…
This implementation describes a pairs strategy that estimates conditional probabilities from a fitted copula applied to each asset’s return ranks. It converts prices to returns, maps returns through marginal cumulative distribution functions, and uses the…
The indicator builds a calendar-year seasonality curve by accumulating daily price changes for each month and day across a selected historical date range. Users can set start and end dates, show or hide the curve’s high and low points, and calculate changes…
This document describes John Ehlers’ Elegant Oscillator, a technical indicator intended to help identify mean-reversion opportunities with improved timing. It first takes a two-bar price difference, then scales that derivative by its root mean square over a…
This indicator applies a Hodrick–Prescott smoother to recent closing prices and draws the resulting trend line on a chart. Its settings specify a 100-bar window and a smoothing parameter of 30; increasing the parameter produces a smoother series. The code…