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 describes an MT5 script intended to identify times of day when an asset has historically moved more. It proposes calculating average movement over a user-selected number of trading days, then reviewing the result in a column chart to help day…
This document is a broad glossary of machine learning and data mining terms, organized by task. It surveys sampling methods, clustering, classification and regression, model evaluation, probabilistic graphical models, neural networks, deep learning,…
ColorZeroLagRVI is described as an oscillator built from four Relative Vigor Index indicators. Its adjustable inputs include factor weights, with each factor controlling the contribution of an RVI component to the combined indicator value. The description…
This research summary examines additional ways to monitor crowding in equity investment factors. Factor crowding refers to a situation in which heavy investment in a factor may weaken its returns or make them less stable. The analysis considers asset…
This indicator extends a moving-average candle display by adding colored dots to show the strength and direction of a trend. It measures the standard deviation of the indicator’s centerline and compares it with two configurable thresholds. When the value…
The discussion addresses how a strategy can show more losing trades than winning trades while its cumulative account value still rises. The reply explains this through the aggregate size of gains and losses: a smaller number of sufficiently large wins can…
This overview introduces ten supervised learning approaches: linear and logistic regression, linear discriminant analysis, decision trees, naive Bayes, k-nearest neighbors, learning vector quantization, support vector machines, bagging and random forests,…
GAPO, or the Gopalakrishnan Range Index Oscillator, is presented as a way to quantify how an instrument’s trading range changes over a chosen lookback period. It uses price action alone: find the highest and lowest prices in the period, take the logarithm of…
This platform support discussion reports sparse cross-sectional coverage for two company growth fields: year-over-year growth in free cash flow and year-over-year growth in adjusted net profit. The author says the free cash flow field has only about 800…
This survey report examines how cryptocurrency policy figures in U.S. voters’ priorities ahead of the 2024 election. It reports that many crypto owners want candidates to address the sector, that a substantial share describe themselves as split-ticket…
This programming note explains how an MQL5 expert advisor can retrieve recent deal information from account history without looping through every record. It selects history from a chosen start time through the current time, gets the final deal ticket, and…
This document describes an equity factor based on intraday volume moving through a low-to-high-to-low cycle. It smooths volume with a nine-minute neighborhood, identifies a peak and the lowest-volume points before and after it, then measures price-change…
The document surveys the deep reinforcement learning agents available through FinRL, which integrates implementations from ElegantRL, Stable Baselines 3, and RLlib. The listed algorithms include value-based, policy-gradient, actor-critic, and multi-agent…
The Pearson approach forms equity pairs by ranking stocks on the correlation of their monthly returns during a formation period. For each stock, it selects the most highly correlated peers and combines their returns into a benchmark portfolio, using either…
The Ehlers Relative Vigor Index (ERVI) is a price oscillator based on the relationship between candle bodies and trading ranges. Its calculation first forms weighted averages over four bars: candle body changes contribute to the numerator, while high-to-low…
This guide explains how FMZ evaluates trading strategies on historical market data. It contrasts simulated Tick backtests, which construct intrabar price events from candles, with live-data Tick backtests, which replay collected tick, depth, and trade…
This report summary introduces entropy pooling as a way to incorporate qualitative or quantitative views into a risk model by updating a probability distribution. It contrasts the approach with the Black–Litterman model, describing broader choices for risk…
The document summarizes research on weighting equity alpha factors through factor-mimicking portfolios (FMPs). It presents FMPs as an alternative representation of alpha signals under a stock covariance model, with linear combinations of factors…
The research note explains how alpha factors can be represented through factor-mimicking portfolios (FMPs) under a stock covariance model. It describes translating linear combinations of alpha factors into corresponding combinations of FMPs, then choosing…
The document explains Parkinson’s historical volatility measure, which uses each period’s high and low prices to estimate return variability under a random-walk assumption. It defines the high-low return as the natural logarithm of the high divided by the…
Polychromatic Momentum combines momentum measurements from multiple lookback periods using a weighted average. The motivation is that a single momentum lookback may stop being suitable as market conditions change, so aggregating periods can reduce dependence…
This stock-selection screen targets main-board shares outside the STAR Market. It combines turnover between 3% and 12%, a daily gain above 1% relative to comparable stocks, and a ratio of 2021 to 2018 revenue greater than 1.1. The accompanying indicator and…
This document describes an indicator that counts consecutive runs of bullish and bearish bars over a user-selected window. It presents the results as a chart, with two vertical-axis choices: the number of runs or the percentage of runs. A smoothed chart is…
This report summary describes fundamental implied returns, or FIR, as a measure of fundamental momentum intended to use more information than conventional measures. FIR accounts for lagged fundamental variables and their time trends, and can be constructed…