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 describes an Expert Advisor that trades crossovers between a faster and a slower moving average. A signal is evaluated when a bar closes: a move above the fast average triggers a buy, while a move below it triggers a sell. The EA can add volume…
This tutorial explains how FMZ adapts Pine scripts for strategy writing, charting, backtesting, and live trading. It outlines platform-specific differences, including where execution settings and precision are configured, contract-code requirements, added…
This research summary examines two responses to a prolonged value-factor drawdown: changing how the factor is constructed and forecasting when its returns may be stronger. It compares conventional cross-sectional valuation with time-series measures of a…
The post describes a proposed A-share stock screen using a turnover-rate range of 3%–12%, market capitalization below 10 billion yuan, and a profitability filter. It then adds a Bollinger Band condition, along with example formula and Python references. The…
The expert adviser described here seeks retracements after unusually strong price movements in USD-based currency pairs. It combines the premise that sharp moves can be followed by pullbacks with a Momentum indicator trigger, including an AUDUSD example…
This stock-selection example screens Chinese equities using a turnover range, year-over-year net profit growth, and the prior day’s trading value. It then ranks qualifying stocks by institutional ownership and selects the highest-ranked names. The rationale…
This research applies macroeconomic momentum signals to active bond trading, aiming to forecast government bond yield direction as well as changes in term and credit spreads. It contrasts active strategies focused on capital gains with passive approaches…
This research summary introduces APM, a stock-selection factor built from differences between morning and afternoon price behavior in Chinese A-shares. Its premise is that informed traders are more active in the morning, making morning price moves a stronger…
This short forum exchange raises a practical concern about transparency in visual quantitative research tools. A user asks for fuller descriptions of how drag-and-drop modules calculate outputs, especially whether feature-generation steps first group data by…
This strategy uses Bollinger Bands in relation to a 200-period moving average to identify directional conditions. It proposes entering on a pullback toward the 20-period average after the relevant band moves beyond the 200-period average. After price closes…
This research note describes a daily equity alpha approach that uses supervised neural networks to generate many candidate factors from designed factor units. It then transforms the original inputs into weak, mutually orthogonal factors and weights them…
This guide outlines a crypto pairs mean-reversion strategy built around cointegration rather than correlation alone. It proposes testing logged price series with the Engle–Granger method, estimating a regression hedge ratio, and checking the resulting spread…
This document describes an automated breakout approach driven by the Color_QEMA_Envelopes_Digit_System indicator. A trade signal is generated when a bar closes with a color that differs from the preceding bar, or when the preceding bar has no color. The…
The document describes a dual-period RSI method that combines a shorter calculation with a longer one to address both retracement entries and longer-term positioning. In the referenced approach, five-week and seventeen-week RSI readings inform entries and…
Recursive analysis helps check whether indicator values depend materially on how many startup candles are available. Recursive formulas use prior values, so an indicator calculated over the full backtest history may differ from one calculated in a dry or…
Recursive indicators depend on preceding values, so their outputs can change when calculations begin with different amounts of historical data. A backtest may use a long requested date range, while a live or dry run may have fewer candles available from the…
The document introduces ALGLIB, a numerical analysis library ported for use with MetaTrader. Its listed capabilities include linear algebra, optimization, interpolation, Fourier transforms, differential equations, statistical tests, and data analysis methods…
This study adapts SinGAN, a multiscale generative adversarial network trained on one sample, to generate financial return sequences. Its pyramid trains progressively across scales: coarse layers represent broad, low-frequency structure, while finer layers…
This report reviews equity factor performance, emphasizing a February 2018 snapshot and trends over a longer historical period. It compares factor information coefficients, which measure association with subsequent returns, and market neutral long-short…
This summary describes a single-stock strategy for Changchun High-Tech, a Chinese pharmaceutical company. It argues that steady fundamentals and stable analyst expectations for earnings growth create a valuation reference point. Using a price-to-earnings…
This note describes an A-share screen for beverage and alcohol related companies. It selects stocks with turnover between 3% and 12% and circulating market value between 5 billion and 10 billion yuan, using industry classifications to identify the target…
The document summarizes research that derives two liquidity factors from high-frequency order-book data, one associated with buy orders and one with sell orders. The factors are then aggregated to monthly frequency for use in stock selection. It reports that…
This edited seminar transcript surveys a Chinese quantitative research program on deep learning, then focuses on AlphaNet, a neural approach to stock factor discovery. It frames a multi-factor process as factor generation, factor combination, and portfolio…
The document outlines a way to run multiple parameterized tasks in BigQuant, a low-code platform where a visual workflow is represented as a graph of modules. A parallel mapping function can dispatch different inputs to a function, and the same pattern can…