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 course-page description outlines a workflow for developing multi-factor investment models, moving from factor testing to evaluation and combination. It highlights checking whether factors are effective and stable, standardizing and neutralizing them,…
The document explains how Bayesian decision theory assigns an observation to the class with the largest posterior probability. It separates the posterior into a class-conditional likelihood and a prior class probability. The prior can be estimated from class…
This study summary describes using recurrent neural networks, including long short-term memory cells, to forecast stock movements separately by industry. The rationale is that firms in one sector may share common influences, while industries can differ in…
This brief indicator description presents a trendless oscillator inspired by Joe DiNapoli’s book Trading with DiNapoli Levels. Its output is rendered as a colored histogram, and the final indicator value is smoothed. The description places it in the…
This report summary describes using gene expression programming, a heuristic inspired by biological evolution, to discover price-volume factors from short-horizon data. Because many candidate factors had weakly monotonic group returns or no excess return in…
This document describes an indicator that adds a three-level trend-strength display to a rounded moving average. It uses the standard deviation of the moving-average indicator and compares that value with two user-set thresholds. When the value lies between…
The Difference2 indicator plots the change between the selected price and its value a chosen number of periods earlier. It presents the result as a histogram and offers a period input, a calculation mode, and a choice of applied price. This makes the same…
This document describes an expanded version of a MACD slope divergence indicator. Its stated additions are optional background coloring for possible channels and support for multiple timeframes. Alongside standard MetaTrader 5 timeframes, it offers three…
This code module supplies plotting and summary routines for quantitative factor research. It formats tables for factor returns, turnover, rank autocorrelation, quantile statistics, and information coefficients. Its chart functions visualize information…
This analysis proposes six dimensions for assessing Chinese brokerage firms’ monthly stock recommendations: absolute returns, return relative to volatility, sector selection, stock-level excess returns, ability to identify emerging winners, and selection…
The document explains the Choppiness Index as a bounded indicator for judging whether price action is trending or moving sideways. It describes the reading inversely to price direction: higher values suggest a greater likelihood of a range, while lower…
The document introduces nonlinear regression as fitting observations with a mathematical function, often a curve, rather than a straight line. It describes minimizing the sum of squared deviations as a way to assess fit and names logarithmic, trigonometric,…
The code implements a Cox–Ingersoll–Ross model for a mean-reverting portfolio, extending an Ornstein–Uhlenbeck model interface. It supports fitting the model to portfolio prices or to two assets, and estimates the long-run mean, reversion speed, and variance…
This article explains how to turn future returns into labels for supervised trading models, arguing that the label should match the instrument, trading horizon, liquidity, and costs of the intended strategy. It first describes using an n-period return as a…
The document describes an A-share stock screen combining daily price movement, market capitalization, profitability, and moving-average conditions. It selects stocks with an intraday range of at least 1%, positive net profit, market value up to 10 billion…
This excerpt introduces a framework for assessing whether stock-selection factors may deliver persistent returns beyond broad market exposure. It distinguishes market-related beta from alpha and presents factor effectiveness as a question of both return…
The author describes an unfinished attempt to build a multiple logistic regression library in MQL5 that can handle a variable number of independent data columns. Earlier functions were hard-coded for particular numbers of predictors, which the author…
The document explains a simple finite-difference indicator for price charts. It first notes that estimating a derivative from the current bar and a future bar requires an unknown future price. Instead, it compares a prior bar with the current bar, producing…
This brief guide introduces several common Python errors and ways to begin diagnosing them. It illustrates how visually similar full-width punctuation can trigger a syntax error, how inconsistent indentation can raise an indentation error, and how a function…
This document outlines a per-contract result tracker and a portfolio-level PnL container. The contract tracker stores an opening position, observed trades, position changes, and cumulative long and short traded volumes and costs. It filters duplicate trade…
This example demonstrates a workflow for analyzing Bitcoin market data across multiple time intervals. It loads minute bars for a specified historical period, configures a transaction-rate assumption, and selects several technical indicators, including ATR,…
The document contains historical ADA/USDT candlestick observations at half-hour intervals. Each row records a timestamp, open, high, low, close, and traded volume, allowing a researcher to inspect price movement and activity or use the series as an input to…
This tutorial introduces Python strings as immutable sequences of characters and explains common operations for working with them. It covers concatenation, length, indexing and slicing, splitting text into lists, and searching with methods such as count,…
This example retrieves historical minute bars for a cryptocurrency symbol from a trading database, using an exchange, interval, and date range as query parameters. It then extracts each bar’s timestamp and closing price and plots the resulting price series…