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.
29,558 documents
This overview presents QLib as an open-source quantitative research platform that supports data preparation, model training, portfolio construction, risk analysis, backtesting, and execution research. It notes support for supervised learning, market-dynamics…
This note proposes a Chinese equity screen using an RSI threshold below 65, membership in the beverage and alcohol import-export industry, and a price below 12. It presents the combination as a way to pair a technical condition with an industry…
This BigQuant forum post presents a SQL query intended to calculate sector-level and market-level returns, compound each series across a rolling window, and derive an information-ratio-like value. The author reports that the underlying daily inputs appear…
This Freqtrade strategy template describes a short-term, long-and-short system using a five-minute chart. It enters when price is above or below a simple moving average calculated on a resampled, longer interval, and a short-period EMA crosses the…
This Chinese-language post outlines an equity screen that selects stocks associated with the metaverse concept, a rising 30-day moving average, and a KDJ bullish crossover. It presents the combination as a way to find stocks with upward price momentum. The…
This document describes a technical stock screen for mainland Chinese equities. It selects stocks whose 14-period RSI is below 65, whose latest high is the highest of the latest two observations, and whose 30-day moving average is rising. The stated…
This post describes a Chinese equity screen that combines a turnover-rate band, a beverage and alcohol industry filter, and positive fund-holding changes. Its proposed final logic also asks for a rising 30-day moving average. Formula and Python examples…
This Chinese stock-screening post combines a price-amplitude condition, a morning-star candlestick signal, and the presence of an outstanding convertible bond. It gives a formula reference and a Python example that checks recent daily prices and…
This indicator framework analyzes price structure on two horizons. Short-lookback internal pivots generate break-of-structure signals for continuation and changes of character for possible reversals; the reversal label CHoCH+ adds a higher-low or lower-high…
This reference surveys common technical indicators and explains several price, risk, valuation, and execution measures with formulas and numerical illustrations. Topics include simple and exponential moving averages, RSI, beta, Sharpe ratio, price momentum,…
This live-monitoring page describes a trend signal system for crypto markets across several candle intervals. It marks an interval as rising or falling and assigns an index that changes as the trend continues; a fresh value of 1 or -1 identifies a new upward…
This code describes a deep learning approach for turning sequential market features into position signals. Its example model uses an LSTM layer followed by dropout and a time-distributed output constrained through a hyperbolic tangent activation. Training…
This proposed Chinese A-share screen looks for stocks associated with the metaverse industry, a rounded-bottom or arc-shaped pattern, and a daily decline between 4% and 5%. The final stated criteria also add PEG below 1. The document includes a Python…
The article describes a stock screen combining daily price amplitude above one, a condition labeled as prior-day main-force control, and a gain exceeding ten percent over 2021. It presents amplitude as a measure of trading fluctuation, the control condition…
This MetaTrader expert advisor uses the nearest ZigZag vertex on a new bar to reverse positions. A vertex at a bar high triggers a buy and closes existing sell positions; a vertex at a bar low triggers a sell and closes existing buy positions. A…
This equity-screening proposal looks for stocks with daily amplitude above 1 that had three consecutive limit-up sessions the previous day. It initially caps the 9:25 a.m. gain below 6%; the refined version adds a lower bound of -3% and requires RSI(14) to…
This article presents a discretionary approach to rotating from an established leading stock or theme into a newer one. It watches for signs of a theme gaining breadth, such as multiple limit-up stocks, rising sector performance, and an increasing count of…
The post asks how to translate the Turtle Trading system’s N measure into contract size. Its proposed calculation uses average true range over a chosen risk window, then divides one percent of risk capital by ATR multiplied by the assumed price tick and…
This proposed Chinese equity screen looks for stocks priced below 12, with at least five moving averages clustered together, and at least two limit-up days during the prior ten days. The document interprets the clustered averages as a relatively stable price…
This meetup Q&A covers practical choices in quantitative strategy design. It says researchers can choose the forward-return horizon used as the target when calculating information coefficients, and points to model-based and scoring templates. For…
The strategy screens Chinese equities using a combination of a 14-day relative strength index below 65, market capitalization between 200 million and 100 billion, and positive profitability. The final description also specifies no losses over the preceding…
This brief description outlines an expert advisor that checks its signals only when a new bar appears. It opens a buy position when the Commodity Channel Index rises above a configurable upper threshold and opens a sell position when the indicator falls…
This stock-selection proposal combines three filters: daily price amplitude above 1, prior-day actual turnover between 3% and 28%, and a company type associated with a market theme. The intended logic is to pair price movement and trading activity with a…
This A-share screening rule combines a turnover range of 3% to 12%, circulating market value from 1 billion to 55 billion yuan, and a bullish most-recent weekly candle. It mixes a trading-activity filter and a size constraint with a price-chart condition…