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.
16,761 documents
This document outlines an Expert Advisor that trades signals from the CronexCCI oscillator. It generates a signal when a bar closes and the indicator cloud changes color. The EA requires the compiled CronexCCI indicator file, and a supporting library is…
This support discussion explains a factor-analysis failure caused by insufficient coverage of a derived price feature. The feature compares the close with the high-low range and then takes a one-period change. Although feature extraction returned data, the…
This proposed screen targets main-board stocks with an intraday amplitude above one and a daily price gain above one percent. It also calls for three technical indicators to register bullish crossovers, then selects up to a chosen number of qualifying…
This strategy studies a daily selection of ten Chinese main-board stocks ranked by free-float market capitalization, from smallest to largest. It excludes stocks marked ST, suspended stocks, companies listed for less than a year, and listings on the STAR…
This study builds a text-derived earnings surprise factor, SUE.txt, to capture post-earnings announcement drift in Chinese equities. It uses analyst report titles and summaries related to earnings forecasts, converts them into word-frequency features, and…
This document describes an Expert Advisor that trades signals from the ColorBears indicator. It generates a signal when a bar closes and the indicator histogram changes color, making the strategy depend on confirmed bar-close changes rather than intrabar…
The document presents a Relative Strength Quality Index, or RSX, as a smoothed alternative to a jagged RSI, alongside a corrected line calculated from the RSX values. It suggests using the corrected line to filter RSX whipsaws or treating its crossing of the…
The article proposes selecting stocks with turnover between 3% and 12%, an external-to-internal trading volume ratio above 1.3, and a daily control reading above 21%. The stated rationale is to find stocks with meaningful trading activity and buying…
The document describes a cross-platform virtual trading library that lets an expert advisor run in simulated and live environments. It presents uses including testing against current prices, optimizing over historical data, pausing live orders while…
This document describes an external Expert Advisor intended to estimate broker commissions during MetaTrader 5 strategy tests when the platform’s built-in commission feature does not produce the desired result. It says the tool supports market, limit,…
These release notes describe changes to a quantitative trading and research platform. Pipeline additions include grouped ranking, filters that test conditions across lookback windows, and several technical factors such as Aroon, fast stochastic, Ichimoku,…
This example describes a daily futures strategy using the Vortex Indicator to identify directional crossovers. It calculates positive and negative vortex movement relative to rolling true range, then opens a long position when the positive line crosses above…
This document outlines a workflow for assembling historical data for a CSI 300 research project. It downloads historical constituent information, retrieves the index membership for each trading date, converts vendor symbols into vn.py format, and saves the…
This indicator evaluates simple one-candle mean-reversion trades by tracking separate rolling equity curves for long and short setups. A long trade is simulated after a down candle and a short trade after an up candle; each is closed one candle later. The…
This article adapts a supervised stock-timing approach to Chinese equities. It describes using nine price- and volume-related features to train a binary classifier: the label is positive when the price 30 trading days later is at least the current price, and…
This document presents a long-only DAX strategy intended for three-minute bars. It enters when the two-period exponential moving average crosses above the four-period average, provided the 20-period average is above the 75-period average and price is above…
This brief description explains an Expert Advisor that trades from the CoeffofLine_true indicator. It generates a signal when the indicator’s histogram crosses its zero level at a bar close, using the crossing direction to trigger a deal. The text is a…
This study evaluates a convolutional neural network that predicts five-day returns across the Chinese stock market. Its baseline uses 2012–2017 data for training and tests on 2018 through October 2021. The authors vary batch size, optimizer, loss function,…
This research framework measures how crowded equity industries are using price and trading activity. It groups candidate measures into trend-oriented indicators, supplementary volume and order-flow measures, and relative comparisons across industries.…
This script builds a Binance BTCUSDT order book backtest and creates visual panels for examining the run. It loads depth snapshots and updates, reconstructs order book deltas, and runs an order book imbalance strategy alongside an actor that samples…
The Expert Advisor trades reversals in the direction of the ColorHMA moving average. It checks for a direction change when a bar closes, then uses that change to generate a trading signal. The document describes the signal rule but gives little detail about…
The document explains how to migrate an existing Nautilus Parquet catalog into the current Arrow representation. The workflow first runs a dry run to inspect supported files, schemas, and layout issues, then converts into a separate new or empty destination.…
The document describes a ProBacktest indicator that tracks strategy profitability by calendar month and year. It initializes capital values, detects date changes, calculates each completed period’s profit from strategy profit and starting capital, and graphs…
The report combines wavelet denoising with a support vector machine to forecast the CSI 300 index time series. It frames market direction as a classification task and price estimation as a regression task, then uses the forecasts to build both long-only and…