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 event-driven equity strategy buys stocks at the open after financial results are announced, selecting companies whose year-over-year net profit attributable to parent shareholders has grown by more than 30%. Eligible stocks are ranked by growth, and the…
The document describes a long-short trend strategy that uses the direction of a 100-period moving average as its momentum signal. It compares the current average with its value 20 trading days earlier: a higher reading triggers a long position, while a lower…
The document describes a short-term stock screen combining a 14-period RSI below 65, three consecutive declining sessions, and a daily price change between -5% and 2.6%. It frames the conditions as a way to find weak stocks that may be positioned for a…
This document describes an Expert Advisor that trades from signals produced by the Stopreversal indicator. It generates a signal when a colored indicator arrow appears at a bar close, and requires the compiled indicator file to be available in the platform's…
This expert-advisor strategy enters trades when a bar closes and the Open Oscillator Cloud changes color, which the document treats as a trend change. It adjusts trade volume according to recent outcomes in each direction: after a specified run of losing…
This report examines whether removing stocks selected by high-frequency multi-factor short portfolios can improve a CSI 300 index-enhancement strategy. It compares three approaches: combine standardized factor scores, use a regression model to forecast…
This document describes a trading robot that sets position volume and stop loss using market volatility. The trader can choose the volatility lookback period, smoothing method, and whether volatility is measured from open and close prices or from the high…
This stock screening proposal selects shares with turnover between 3% and 12%, seven consecutive days of falling prices, and positive net buying attributed to major market participants on the prior day. The rationale is to look for heavily declining stocks…
This document describes an automated strategy that trades signals from the XWPR_Histogram_Vol_Direct indicator. A signal occurs when a bar closes and the histogram changes direction, shown by a change in the color of its star markers. The approach therefore…
The document gives parameter settings for a EURGBP strategy that plots a channel over a specified bar period and uses an operating time window and a stop loss scaled to channel width. It reports a five-minute historical test spanning 2006 to 2009, with 2,523…
The document proposes a Chinese equity screen for stocks classified in the metaverse industry. It selects names with a volume ratio above 1.5 and below 6, and a price increase under 6% at 9:25. The stated rationale is to combine elevated but bounded trading…
This Chinese-language article introduces a customizable stock-selection strategy on a quantitative trading platform. It describes combining five selection rules, mainly intended to find stocks that have fallen sharply and begun to stabilize, with some rules…
This FAQ describes the scope and practical use of an educational financial reinforcement learning library. It covers supported data sources, feature inputs such as sentiment, training options, reward functions, hyperparameter tuning, and algorithm choices.…
The document explains how to build a fund backtest in a platform whose standard workflow does not directly support fund data. The example strategy buys when a short moving average crosses above a longer one and sells when it crosses below. It describes…
This documentation entry directs coding agents to start from complete LumiBot examples for either AI-based or ordinary Python strategies. It describes the strategy lifecycle at a high level: create agents during initialization and invoke them during each…
This forum post raises a data-preparation problem in an LSTM trading strategy. The author reports that filtering rows before rolling sequence windows can remove observations that should remain part of the temporal context, causing later observations to shift…
The article compares two ways to build equity strategies: train a predictive model on chosen factors and a defined stock universe, or specify screening conditions directly. The AI approach can be quicker to assemble, but its behavior may be hard to diagnose…
This indicator identifies consecutive bullish White Soldiers or bearish Black Crows candle sequences. Its parameters let the user choose how many candles must appear in a row and optionally require each candle's real body to exceed a chosen share of its full…
The report reassesses valuation, growth, technical, and risk factors in Chinese A-shares after removing industry and style influences. Its core method is to adjust factor data for exposures such as industry, market capitalization, or beta, then test whether…
This Chinese-language article presents a daily stock screen using three conditions: amplitude above 1, a controlling-shareholder measure above 21 in absolute value, and the closing price above the previous day’s low. It provides example implementations in…
Fundamental quantitative investing applies statistical methods and algorithms to company accounts, industry information, and macroeconomic data to rank stocks by estimated value or quality. The document describes analyzing profitability, financial strength,…
This competition entry modifies a Deep Alpha convolutional neural network by supplying five time slices for each of 98 factors, rather than using a single slice. The network structure and most parameters remain close to the original model because training…
This short description outlines a symmetric breakout rule. It buys or covers a short position when price moves above the high of a chosen number of prior bars, and sells short when price falls below the low of that lookback window. The lookback length is…
The article describes an integrated order flow imbalance factor built from changes in bid and ask quantities across five limit order book levels. It explains how each level’s imbalance can be normalized by typical depth, then combined with principal…