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 explains a least-significant-digit radix sort that processes numeric values byte by byte, using 8-bit digits. It presents an MQL implementation intended for large arrays and describes support for several integer and floating-point types,…
This Chinese-language research summary describes a stock-selection factor built from quarterly profitability data. It defines a trend measure as the sensitivity of profitability to time in a linear regression, with separate versions based on…
This indicator turns confirmed swing highs and lows into support or resistance zones, then ranks the zones to reduce chart clutter. Pivots must clear a minimum displacement relative to ATR; each accepted pivot becomes a band whose width is also tied to ATR.…
The document presents the components of the Traders Dynamic Index (TDI), an indicator built from the relative strength index. It calculates a central average of RSI values, surrounds it with bands based on their standard deviation, and plots additional short…
This document explains a custom MetaTrader 5 MACD indicator that adapts its smoothing to market conditions. It calculates the squared Pearson correlation between closing prices and bar index over a configurable lookback, then uses that value to blend two…
The document presents an A-share screening idea combining metaverse industry classification with relative trading volume between 1.5 and 6 times a reference average. It also uses a closing-price ceiling of 18.5 and, in its final version, a…
This BigQuant forum answer explains how to use a different feature set in each iteration of a rolling model workflow. The example loop updates training and test start and end dates for each rolling window, disables the backtest module during model runs, and…
This report section examines Ethereum’s 2024 market structure using ownership concentration, holder and supply buckets, liquid balances, and valuation measures such as MVRV and NUPL. It compares Ethereum’s concentration patterns with Bitcoin’s and discusses…
The article reviews research on the 2016 launch of Morningstar’s sustainability ratings for U.S. mutual funds. The ratings use portfolio holdings and company ESG scores to assign funds one to five stars within their categories; the star display appears more…
This research summary examines whether sell-side analysts’ earnings forecasts change as they issue more forecasts during a day. It frames decision fatigue as a shift from deliberate reasoning toward faster, more heuristic judgments. Using analyst forecast…
This documentation explains design choices behind TqSdk, a Python trading software development kit. It aims to avoid imposing a strategy model: users can fetch data and issue orders freely, while examples demonstrate possible applications instead of…
The report describes an asset allocation approach that measures cycle states and uses machine learning to estimate the probability that assets will outperform one another. It reviews macroeconomic timing frameworks, then describes cycle factors derived from…
The third-generation XMA is presented as a moving-average variant designed to reduce lag as the averaging period increases. The method is attributed to Dr. Manfred Dürschner, and this implementation uses a parameter value of lambda equal to 2; the source…
This tutorial surveys support vector machines, k-nearest neighbors, naive Bayes, and the perceptron as lightweight classifiers for relatively small datasets and feature sets. It explains SVM’s maximum-margin boundary, the role of support vectors, soft…
The document proposes screening Chinese A-share stocks using a daily amplitude threshold, a price condition around 18.5 yuan, and prior-day turnover between 3% and 28%. It explains these filters as ways to select stocks with notable price movement, a chosen…
The document describes a Better Volume indicator that classifies bars using volume, price range, candle direction, and estimated volume at the bid or ask. It colors a volume histogram for several conditions: high-volume wide-range up or down bars,…
The document presents a way to estimate how often a one-minute Chinese convertible-bond bar closes above its open after three consecutive up bars. It converts each bar’s return into a binary up-or-not indicator, scans the series for three up bars, and counts…
This review of factor performance during the 2018–2020 quant crisis examines why diversified equity strategies struggled. It analyzes standard size, value, investment, profitability, and momentum factors, alongside portfolios formed by sorting stocks on size…
This short discussion explains a label distribution chart used when building an AI trading strategy. The horizontal axis represents label identifiers, and the vertical axis shows how many observations belong to each label. The chart can reveal labels with…
The document outlines nontraditional ways to study NFT projects, using CryptoPunks as its example. It proposes tracking unique holder wallets to gauge ownership distribution and concentration, and first-time buyers to assess whether new participants are…
MyRsi with Noise Elimination Technology is an RSI-style indicator attributed to John Ehlers and described as using a form of Kendall autocorrelation to filter signals. This implementation permits the user to select the input price series instead of always…
The document explains the Detrended Price Oscillator (DPO) as the difference between a closing price and its simple moving average over a chosen period. By subtracting the moving average, the indicator filters out some of the broader price direction,…
This brief indicator description explains Acceleration Bands, attributed to Price Headley, as bands derived from the daily price range. It identifies two configurable inputs: the calculation period and a factor that controls how widely the bands expand. The…
This indicator combines the distance between ADX and ADXR with the relative change in ATR to describe trend development and volatility together. The author argues that ADX alone can miss changes in volatility, while ATR alone is expressed in absolute price…