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 Chinese equity screen selects main-board stocks associated with the robotics theme, with turnover between 3% and 12%, circulating market value below 10 billion yuan, and more than 365 days since listing. The page provides example selection logic and…
The note describes an equity screen tied to 2021 that selects stocks with at least five overlapping moving averages and a positive return below 35% over the prior 10 days. It interprets clustered averages as a sign of a relatively stable price trend and the…
Algorithmic trading turns explicit rules based on variables such as price, timing, quantity, or mathematical models into instructions that monitor markets and place orders. The document illustrates a moving-average crossover and surveys strategy families…
This Chinese stock screen combines a 2021 listing-year condition, daily high-to-low amplitude above one percent, and company scale above 200 million yuan. The article proposes a stricter variant that also requires the stock’s share of total industry…
The document outlines a strategy that dynamically evaluates macroeconomic event factors and selects those more closely associated with asset movements. It considers more than thirty indicators spanning economic growth, inflation, monetary conditions, and…
This overview introduces ten machine learning methods and sketches how they work, with examples of possible financial uses. It covers linear and logistic regression, K-nearest neighbors, support vector machines, decision trees, random forests, neural…
The document explains a lightweight chart indicator that turns user-defined order signals into a visual backtest. Signals specify signed quantities, and the engine applies them at the next bar’s open with a configurable spread. It tracks net position,…
This guide interprets the schedule, asset rules, position limits, and scoring criteria for a stock-trading competition. It recommends planning development and simulation time in advance, describing strategy logic clearly, and accounting for the specified…
The document describes a short-term stock screen based on two daily conditions: an increase in reported position share above 5% and a maximum decline between 4% and 5%. The intended interpretation is that a stock seeing notable buying interest despite a…
This indicator compares price pivots with ten momentum and volume measures, including RSI, MACD, momentum, OBV, stochastic, and Chaikin Money Flow. It counts how many enabled oscillators show each of four divergence types at the same pivot: regular bullish…
This research summary describes ranking international liquid stocks with a random forest trained on technical features. Rather than forecasting exact returns, the model estimates the likelihood that a stock will outperform an average-return threshold. The…
The document summarizes an equity factor study on whether analyst attention predicts future company fundamentals and stock returns. It proposes adjusting a conventional analyst-coverage measure with a linear regression that removes effects associated with…
This overview explains how historical open, high, low, close, and volume data supports cryptocurrency strategy research. It describes OHLCV as price and traded-volume information aggregated over a time interval, and notes that crypto’s continuous trading,…
This introductory tutorial explains how to build, backtest, and simulate a daily single-stock strategy in the MindGo platform. It outlines a two-part strategy framework: initialize account settings once, then run trading logic on each active trading…
The document explains several bare candlestick patterns: morning and evening stars, bullish and bearish engulfing patterns, and red or black three-soldier sequences. It assigns bullish or bearish interpretations to these formations and suggests using stars…
This document describes a trading system based on the XMA Range Bands indicator, identified as a universal Keltner channel. It says the system generates a trade signal when a bar closes with price inside the channel boundaries. The description gives the…
The post defines bullish and bearish three-candle patterns using consecutive closes, close locations within each candle, and limited opposing shadows. It proposes reversing positions when the opposite pattern appears: bullish formations close shorts and open…
The article proposes screening Chinese stocks in the metaverse industry for an opening price near the 10-day moving average and repeated moving-average crossovers. Its initial description asks for at least five moving averages to overlap, but the final rule…
The document presents an A-share stock screen based on a price-range threshold, the presence of an outstanding convertible bond name, and a condition involving fewer than 20 bars. It frames the range and bar-count filters as ways to find active stocks and…
This Chinese-language forum post raises a backtesting problem: gaps in stored Bitcoin market data can leave an open position without later bars on which the strategy could close it. The example describes a long period of missing exchange candles and asks how…
FinRL-Meta addresses a research infrastructure problem: deep reinforcement learning has potential in finance, but researchers need realistic market environments and shared benchmarks to develop and compare methods. The document contrasts this need with…
This indicator applies Symbolic Aggregate approXimation (SAX) to search for historical price windows resembling the latest closed-bar window. It z-normalizes each window to emphasize shape, compresses it into segment averages, and encodes those values as a…
This article explains the event layer of an event-driven trading backtester. It describes an in-memory queue that routes events between system components and defines four event types: market updates trigger strategy evaluation, signals convey a symbol,…
This installment of an event-driven backtesting series explains how to summarize portfolio performance from an equity curve. It describes three measures: annualized Sharpe ratio, maximum peak-to-trough drawdown, and drawdown duration, defined as the number…